Daily Papers

Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no ground-truth dataset exists to characterize the resulting threats. We construct the first labeled dataset of malicious agent skills by behaviorally verifying 98,380 skills from two community registries, confirming 157 malicious skills with 632 vulnerabilities. These attacks are not incidental. Malicious skills average 4.03 vulnerabilities across a median of three kill chain phases, and the ecosystem has split into two archetypes: Data Thieves that exfiltrate credentials through supply chain techniques, and Agent Hijackers that subvert agent decision-making through instruction manipulation. A single actor accounts for 54.1\% of confirmed cases through templated brand impersonation. Shadow features, capabilities absent from public documentation, appear in 0\% of basic attacks but 100\% of advanced ones; several skills go further by exploiting the AI platform's own hook system and permission flags. Responsible disclosure led to 93.6\% removal within 30 days. We release the dataset and analysis pipeline to support future work on agent skill security.

AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions. Because a skill is at once code and agent-facing instruction, it introduces a supply chain dependency whose risk is neither pure code nor pure prompt. Detection tools have never been measured against verified ground truth spanning this hybrid space, leaving their effectiveness unknown and wild-only evaluations biased. We present MalSkillBench, the first runtime-verified benchmark of malicious agent skills: 3,944 malicious skills labeled along a three-dimensional taxonomy of 108 cells. Of these, 3,214 come from a closed-loop Generate-Verify-Feedback pipeline admitting only samples whose malicious behavior fires inside a Docker sandbox under system-call monitoring and an LLM judge; we add 703 in-the-wild and 4,000 matched benign skills. Our measurements are consistent: code injection reaches 94.5% verification yield but prompt injection only 75.8%, the same fragility that later makes it hard to detect; the wild sample is narrow, dominated by one cryptocurrency-theft campaign (86.6% one behavior, 81% from two accounts) with a small but architecturally new tail attacking the agent control plane; the strongest skill-specific detector reaches 98.4% recall on code injection yet collapses on prompt-injection and agent-control attacks, and wild-only scoring swings the ranking by up to 66 recall points; supply-chain scanners and prompt-injection defenses each see only half of a skill, and no combination recovers the code-instruction relationship. Detecting malicious skills therefore requires reasoning jointly over task intent, code, and instructions. We release the dataset, pipeline, baselines, and results.

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills.

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a significant yet uncharacterized attack surface. We conduct the first large-scale empirical security analysis of this emerging ecosystem, collecting 42,447 skills from two major marketplaces and systematically analyzing 31,132 using SkillScan, a multi-stage detection framework integrating static analysis with LLM-based semantic classification. Our findings reveal pervasive security risks: 26.1% of skills contain at least one vulnerability, spanning 14 distinct patterns across four categories: prompt injection, data exfiltration, privilege escalation, and supply chain risks. Data exfiltration (13.3%) and privilege escalation (11.8%) are most prevalent, while 5.2% of skills exhibit high-severity patterns strongly suggesting malicious intent. We find that skills bundling executable scripts are 2.12x more likely to contain vulnerabilities than instruction-only skills (OR=2.12, p<0.001). Our contributions include: (1) a grounded vulnerability taxonomy derived from 8,126 vulnerable skills, (2) a validated detection methodology achieving 86.7% precision and 82.5% recall, and (3) an open dataset and detection toolkit to support future research. These results demonstrate an urgent need for capability-based permission systems and mandatory security vetting before this attack vector is further exploited.

Large Language Model (LLM) agents increasingly rely on third-party skills that operate within privileged execution environments and routinely handle sensitive credentials, yet how these credentials are leaked remains largely unexplored. To fill this gap, we present the first large-scale empirical study on credential leakage in agent skills. From 170,226 artifacts on SkillsMP, the largest open-source skill marketplace, we sampled 17,022 skills via stratified random sampling and analyzed each through static secret extraction (regex and AST parsing), dynamic sandbox testing with mock credentials, and cross-referencing developer intent against runtime behavior. Our analysis identifies 520 affected skills containing 1,708 security issues, and yields a taxonomy of 10 leakage patterns. Three findings stand out. First, 76.3% of cases require jointly analyzing natural-language descriptions and programming logic, showing that credential exposure in skills is fundamentally cross-modal. Second, debug logging accounts for 73.5% of vulnerabilities because agent frameworks feed stdout into the LLM context window, turning routine debugging into a credential exposure vector. Third, 89.6% of leaked credentials are immediately exploitable -- 92.5% during routine execution without elevated privileges -- and the fork-based distribution model defeats remediation, as secrets removed from 107 upstream repositories persist across 50+ independent forks. Following responsible disclosure, all malicious skills have been removed and 91.6% of hardcoded cases remediated. We release our dataset, taxonomy, and detection pipeline to support future agent security research.

AI agents are increasingly interacting within shared online environments, creating new operational security risks. We analyze activity on Moltbook, a Reddit-style social platform where AI agents--typically configured and overseen by human operators--post and interact with one another at scale. Using a dataset of 228,684 posts produced by more than 39,500 accounts over a seventeen-day observation window, we combine semantic clustering of high-engagement posts with LLM-assisted classification of harmful content and manual review of high-risk samples. The analysis identifies 98 thematic discourse clusters spanning agent infrastructure, autonomy debates, and financial activity. While most observed content was benign, 18.28% of posts contained toxic, manipulative, or malicious material. We cluster malicious content and identify 74 classes of malicious behavior, including credential harvesting attempts, host-execution instructions, proxy routing guidance, and efforts to install untrusted agent skills. Harmful content frequently appeared within mainstream operational discussions about agent functionality. We also document coordinated posting campaigns capable of generating thousands of posts in minutes.

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverages standard skill composition to reconstruct and execute an attacker-specified payload. The attack partitions an encrypted payload across multiple benign-looking skill invocations and activates only under a predefined trigger. SkillTrojan also supports automated synthesis of backdoored skills from arbitrary skill templates, enabling scalable propagation across skill-based agent ecosystems. To enable systematic evaluation, we release a dataset of 3,000+ curated backdoored skills spanning diverse skill patterns and trigger-payload configurations. We instantiate SkillTrojan in a representative code-based agent setting and evaluate both clean-task utility and attack success rate. Our results show that skill-level backdoors can be highly effective with minimal degradation of benign behavior, exposing a critical blind spot in current skill-based agent architectures and motivating defenses that explicitly reason about skill composition and execution. Concretely, on EHR SQL, SkillTrojan attains up to 97.2% ASR while maintaining 89.3% clean ACC on GPT-5.2-1211-Global.

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills. In this paper, we present the first large-scale measurement study of harmful skills in agent ecosystems, covering 98,440 skills across two major registries. Using an LLM-driven scoring system grounded in our harmful skill taxonomy, we find that 4.93% of skills (4,858) are harmful, with ClawHub exhibiting an 8.84% harmful rate compared to 3.49% on Skills.Rest. We then construct HarmfulSkillBench, the first benchmark for evaluating agent safety against harmful skills in realistic agent contexts, comprising 200 harmful skills across 20 categories and four evaluation conditions. By evaluating six LLMs on HarmfulSkillBench, we find that presenting a harmful task through a pre-installed skill substantially lowers refusal rates across all models, with the average harm score rising from 0.27 without the skill to 0.47 with it, and further to 0.76 when the harmful intent is implicit rather than stated as an explicit user request. We responsibly disclose our findings to the affected registries and release our benchmark to support future research (see https://github.com/TrustAIRLab/HarmfulSkillBench).

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly hijack an agent's action space, such as file writes, shell commands, and network requests, despite existing safeguards. We introduce Document-Driven Implicit Payload Execution (DDIPE), which embeds malicious logic in code examples and configuration templates within skill documentation. Because agents reuse these examples during normal tasks, the payload executes without explicit prompts. Using an LLM-driven pipeline, we generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories. Across four frameworks and five models, DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses. Static analysis detects most cases, but 2.5% evade both detection and alignment. Responsible disclosure led to four confirmed vulnerabilities and two fixes.

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability expansion, it also introduces a semantic supply-chain risk in which natural-language metadata and instructions can affect which skills are admitted, surfaced, selected, and loaded. We study SKILL.md - only attacks across three registry-facing stages of the Agent Skill lifecycle, using real ClawHub skills and realistic registry mechanisms. In Discovery, short textual triggers can manipulate embedding-based retrieval and improve adversarial skill visibility, achieving up to 86% pairwise win rate and 80% Top-10 placement. In Selection, description-only framing biases agents toward functionally equivalent adversarial variants, which are selected in 77.6% of paired trials on average. In Governance, semantic evasion strategies cause malicious skills to avoid a blocking verdict in 36.5%-100% of cases. Overall, our results show that SKILL.md is not passive documentation but operational text that shapes which third-party capabilities agents find, trust, and use.

LLM agents acquire new capabilities by downloading skills from open registries. Instead of browsing these catalogs manually, developers typically ask the agent to recommend and install a skill. This convenience hides a risk: agents frequently invent names for skills that exist in no registry. We term this flaw skill name hallucination. A fake name may seem harmless, but it opens the door to supply-chain attacks. Because registries rarely verify publishers, an adversary can prompt the agent, collect the fake names it returns, pre-register malicious skills under them, and wait for a victim to install the payload. We conducted the first large-scale measurement of skill name hallucination, evaluating 15,000 prompts across 12 configurations (4 standalone LLMs and 8 agents). We conservatively counted a name as hallucinated only if it was missing from all live registries and GitHub. The results reveal a systemic vulnerability: every configuration hallucinates. Rates average 36.0% for standalone LLMs and 36.9% for agents, rising to 43.1% on real-world developer questions. In total, the systems generated 5,669 distinct hallucinated names. Crucially, these names are not random noise. Agents repeat the same fake names across prompts and models, giving attackers highly reliable targets to hijack. Finally, we tested four model-level defenses and found a severe conflict between security and usability. The strongest, retrieval grounding, cut the hallucination rate from 40.8% to 3.2% but crippled usefulness: even the best-defended system recommended the correct skill only about one in six times. Skill name hallucination is thus a highly exploitable vulnerability requiring minimal attacker effort. Fixing it cannot rely on prompt engineering or model tuning alone. It demands ecosystem-wide structural changes: registry-level name reservations and verified recommendation pipelines.

Agentic systems increasingly rely on reusable procedural capabilities, a.k.a., agentic skills, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of seven design patterns capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal representation times scope taxonomy describing what skills are (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.

With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security challenges, primarily stemming from semantic-behavioral inconsistency and inter-skill combinatorial risks, where individually benign skills induce malicious behaviors during collaborative invocation. To address these vulnerabilities, we propose SkillProbe, a multi-stage security auditing framework driven by multi-agent collaboration. SkillProbe introduces a "Skills-for-Skills" design paradigm, encapsulating auditing processes into standardized skill modules to drive specialized agents through a rigorous pipeline, including admission filtering, semantic-behavioral alignment detection, and combinatorial risk simulation. We conducted a large-scale evaluation using 8 mainstream LLM series across 2,500 real-world skills from ClawHub. Our results reveal a striking popularity-security paradox, where download volume is not a reliable proxy for security quality, as over 90% of high-popularity skills failed to pass rigorous auditing. Crucially, we discovered that high-risk skills form a single giant connected component within the risk-link dimension, demonstrating that cascaded risks are systemic rather than isolated occurrences. We hope that SkillProbe will inspire researchers to provide a scalable governance infrastructure for constructing a trustworthy Agentic Web. SkillProbe is accessible for public experience at skillhub.holosai.io.

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform in this emerging paradigm, introduces an extensible skill ecosystem that allows third-party developers to inject behavioral guidance through lifecycle hooks during agent initialization. While this design enhances automation and customization, it also opens a novel and unexplored attack surface. In this paper, we identify and systematically characterize guidance injection, a stealthy attack vector that embeds adversarial operational narratives into bootstrap guidance files. Unlike traditional prompt injection, which relies on explicit malicious instructions, guidance injection manipulates the agent's reasoning context by framing harmful actions as routine best practices. These narratives are automatically incorporated into the agent's interpretive framework and influence future task execution without raising suspicion.We construct 26 malicious skills spanning 13 attack categories including credential exfiltration, workspace destruction, privilege escalation, and persistent backdoor installation. We evaluate them using ORE-Bench, a realistic developer workspace benchmark we developed. Across 52 natural user prompts and six state-of-the-art LLM backends, our attacks achieve success rates from 16.0% to 64.2%, with the majority of malicious actions executed autonomously without user confirmation. Furthermore, 94% of our malicious skills evade detection by existing static and LLM-based scanners. Our findings reveal fundamental tensions in the design of autonomous agent ecosystems and underscore the urgent need for defenses based on capability isolation, runtime policy enforcement, and transparent guidance provenance.

OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational privileges introduce critical security vulnerabilities, transforming model errors into tangible system-level threats such as sensitive data leakage, privilege escalation, and malicious third-party skill execution. Existing security measures for the OpenClaw ecosystem remain highly fragmented, addressing only isolated stages of the agent lifecycle rather than providing holistic protection. To bridge this gap, we present ClawKeeper, a real-time security framework that integrates multi-dimensional protection mechanisms across three complementary architectural layers. (1) Skill-based protection operates at the instruction level, injecting structured security policies directly into the agent context to enforce environment-specific constraints and cross-platform boundaries. (2) Plugin-based protection serves as an internal runtime enforcer, providing configuration hardening, proactive threat detection, and continuous behavioral monitoring throughout the execution pipeline. (3) Watcher-based protection introduces a novel, decoupled system-level security middleware that continuously verifies agent state evolution. It enables real-time execution intervention without coupling to the agent's internal logic, supporting operations such as halting high-risk actions or enforcing human confirmation. We argue that this Watcher paradigm holds strong potential to serve as a foundational building block for securing next-generation autonomous agent systems. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and robustness of ClawKeeper across diverse threat scenarios. We release our code.

Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.

Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill versions. Each row pairs redacted SKILL.md content and sanitized bundled files where present with a final ClawScan registry verdict and evidence from three scanner families: VirusTotal, static heuristic analysis, and NVIDIA SkillSpector. Rather than estimating malicious-skill prevalence, we study scanner disagreement. The three scanners rarely flag the same skills: any pair overlaps on at most 10.4% of their combined positives, only 0.69% of skills are flagged by all three, and 81.9% of flagged skills are identified by a single scanner. The disagreement is structured by attack surface. SkillSpector, which raises semantic agentic-risk advisories rather than malware-reputation signals, is positive for 19,209 of 25,504 suspicious rows (75.3%) but only 14 of 206 malicious rows (6.8%). The malicious-verdict region shows the inverse profile: 150 of 206 malicious rows (72.8%) are VirusTotal-positive, consistent with bundled-code malware evidence. These results show that agent-skill security requires layered governance, not single-scanner allow/block decisions. The corpus is released as a sanitized silver-standard dataset: labels are the registry's automated verdicts, not human-annotated ground truth, and the release represents an early, versioned snapshot intended to support the community while a human-annotated subset is developed. Further research is encouraged, including models tailored for skill-security triage.

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files. SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions. We evaluate frontier LLMs on SkillInject, measuring both security in terms of harmful instruction avoidance and utility in terms of legitimate instruction compliance. Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models, often executing extremely harmful instructions including data exfiltration, destructive action, and ransomware-like behavior. They furthermore suggest that this problem will not be solved through model scaling or simple input filtering, but that robust agent security will require context-aware authorization frameworks. Our benchmark is available at https://www.skill-inject.com/.

Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A practically dangerous injection must stay invisible: if executing the payload derails the user's legitimate task, the resulting failure signal invites inspection of the skill. We therefore evaluate attacks by Attack Success Rate, which requires the injected payload to execute and the user's task to still pass its verifier in the same trial. Prior skill-poisoning attacks face a reliability-stealth trade-off under this lens: YAML-header injections are reliably loaded but easily inspected, whereas stealthier body injections that place explicit malicious commands in the skill prose are less reliable because out-of-context commands invite the agent's own suspicion. We introduce POISE, a position-aware attack that compresses the trigger into a single, benign-looking body instruction, placing it at a feasible position and using a context-aware generator to blend it with nearby setup or prerequisite steps. On Skill-Inject with codex+gpt-5.2, POISE achieves an 89.3% ASR, 28.0 points above a random-placement body baseline and 2.6 points above a YAML-only baseline, while retaining the stealth advantage of body placement. That stealth is the decisive margin: because legitimate skill bodies naturally require privileged tool operations, LLM scanners are hyper-sensitive, falsely flagging 74.6% of clean skills on average across four judges and both benchmarks. Blending into these false alarms, POISE causes only 5.6% of poisoned variants to gain a new high-risk alert over their clean baselines, rendering current static defenses ineffective.

LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown Skill is rendered to HTML, HTML comment blocks can become invisible to human reviewers, yet the raw text may still be supplied verbatim to the model. In experiments, we find that DeepSeek-V3.2 and GLM-4.5-Air can be influenced by malicious instructions embedded in a hidden comment appended to an otherwise legitimate Skill, yielding outputs that contain sensitive tool intentions. A short defensive system prompt that treats Skills as untrusted and forbids sensitive actions prevents these malicious tool calls and instead surfaces the suspicious hidden instructions.

Self-evolving agents increasingly convert interaction histories into reusable skills that persist beyond individual tasks. While prior work studies memory and retrieval poisoning, such attacks only affect agents when poisoned records are retrieved as context. We uncover a new and more fundamental risk: poisoned experiences can be transformed by the agent itself into durable behavioral artifacts. We present SkillJack, the first attack that exploits the experience-to-skill pipeline of self-evolving agents. Instead of directly manipulating runtime context, SkillJack hijacks the agent's own learning process to implant malicious behaviors into its reusable skill repertoire. We identify three key properties of this transformation: sanitization whitewashing, where malicious intent is obscured during skill extraction; cross-layer promotion, where transient experiences become persistent capabilities; and persistence isolation, where the attack survives removal of its original source records. We evaluate SkillJack on two representative systems, SkillX and Anything2Skill, using a shared dataset of 150 trajectories across four policy-risk categories. Results show that skill extraction substantially reduces attack detectability: in SkillX, safety detection drops from 98.5\% for poisoned trajectories to 11.4\% for extracted skills, while Anything2Skill shows a similar effect. Meanwhile, the implanted skills remain effective, achieving attack success rates of 56.2\% and 89.2\% on the two systems, respectively. Furthermore, 80.0\% of skill-mediated attacks persist after deleting the original poisoned records, and some skills unintentionally activate on benign queries. Our findings reveal skill evolution as a new attack surface and motivate provenance-aware skill lifecycle protection. Our code is available at https://github.com/Tencent/AI-Infra-Guard/research/skilljack.

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces--shell, filesystem, containers, and messaging--introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy of 190 advisories filed against OpenClaw, an open-source AI agent runtime, organized by architectural layer and trust-violation type. Vulnerabilities cluster along two orthogonal axes: (1) the system axis, reflecting the architectural layer (exec policy, gateway, channel, sandbox, browser, plugin, agent/prompt); and (2) the attack axis, reflecting adversarial techniques (identity spoofing, policy bypass, cross-layer composition, prompt injection, supply-chain escalation). Patch-differential evidence yields three principal findings. First, three Moderate- or High-severity advisories in the Gateway and Node-Host subsystems compose into a complete unauthenticated remote code execution (RCE) path--spanning delivery, exploitation, and command-and-control--from an LLM tool call to the host process. Second, the exec allowlist, the primary command-filtering mechanism, relies on a closed-world assumption that command identity is recoverable via lexical parsing. This is invalidated by shell line continuation, busybox multiplexing, and GNU option abbreviation. Third, a malicious skill distributed via the plugin channel executed a two-stage dropper within the LLM context, bypassing the exec pipeline and demonstrating that the skill distribution surface lacks runtime policy enforcement. The dominant structural weakness is per-layer trust enforcement rather than unified policy boundaries, making cross-layer attacks resilient to local remediation.

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have shown that adversaries can easily manipulate agents into performing harmful actions, such as leaking API keys, deleting user data, or initiating unauthorized transactions. Evaluating agent security is inherently challenging, as agents operate in dynamic, untrusted environments involving external tools, heterogeneous data sources, and frequent user interactions. However, realistic, controllable, and reproducible environments for large-scale risk assessment remain largely underexplored. To address this gap, we introduce the DecodingTrust-Agent Platform (DTap), the first controllable and interactive red-teaming platform for AI agents, spanning 14 real-world domains and over 50 simulation environments that replicate widely used systems such as Google Workspace, Paypal, and Slack. To scale the risk assessment of agents in DTap, we further propose DTap-Red, the first autonomous red-teaming agent that systematically explores diverse injection vectors (e.g., prompt, tool, skill, environment, combinations) and autonomously discovers effective attack strategies tailored to varying malicious goals. Using DTap-Red, we curate DTap-Bench, a large-scale red-teaming dataset comprising high-quality instances across domains, each paired with a verifiable judge to automatically validate attack outcomes. Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models, spanning security policies, risk categories, and attack strategies, revealing systematic vulnerability patterns and providing valuable insights for developing secure next-generation agents.

LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution. In this work, we conduct a systematic investigation into how well current agent systems recognize and avoid such risks. To support quantitative and qualitative evaluation, we construct OpenSkillRisk, a dedicated safety benchmark containing 263 risky skills collected from public skill marketplaces. We classify these skills into seven categories based on their threat types and pair each skill with a standardized user task and a corresponding sandbox for controlled evaluation. Distinct from prior benchmarks, OpenSkillRisk not only covers more realistic and diverse unsafe scenarios, but also provides a fine-grained analysis to diagnose the behavioral patterns of agents in such scenarios. We conduct comprehensive experiments covering three mainstream CLI agent frameworks and thirteen state-of-the-art LLMs. Experimental results show that no tested system handles risky skills reliably: even the safest configurations still execute unsafe actions in about 17% of cases. Context-dependent and system-level risks are especially difficult for current agent systems to avoid. Our behavioral analysis reveals three recurring failure patterns: agents may fail to recognize the risk, recognize it but fail to intervene before acting, or follow skill instructions beyond the user's intended scope. These findings highlight the need to improve both risk reasoning in LLMs and execution control in agent frameworks.

Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using accumulated trajectories. However, they struggle in cold-start settings, where only an initial, imperfect skill is available. Consequently, skill construction defaults to expert authoring or one-shot LLM generation. Expert-authored skills are costly and may not align with how LLM agents actually execute tasks, while one-shot generated skills can be syntactically well formed yet behaviorally weak. To bridge this gap, we propose SkillRevise, an execution-grounded framework designed to iteratively refine these initial skills. SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits. By re-executing candidates and measuring empirical utility, it systematically retains the optimal skill version. Evaluated across three benchmarks and five LLMs, SkillRevise substantially outperforms one-shot baselines, improving the base agent's success rate on SkillsBench from 36.05% to 61.63%. Furthermore, the revised skills exhibit strong cross-model transferability, capturing generalized procedural knowledge over model-specific artifacts.

LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL.md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.

Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored. In this paper, we present SkillSec-Eval, a lifecycle-aware framework for systematically evaluating the security of reusable agent skills. We first characterize the skill lifecycle and develop a threat taxonomy spanning repository admission, semantic retrieval, planner selection, execution, and skill evolution. We then instantiate this taxonomy in SkillSec-Eval and conduct a comprehensive empirical evaluation using a repository of 327 real-world skills. Our study demonstrates that vulnerabilities arise at multiple lifecycle stages beyond execution, highlighting the need for lifecycle-aware security analysis of reusable agent skills.

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw (228,000 GitHub stars) and Anthropic Agent Skills (75,600 stars) -- has introduced a critical supply chain attack surface. The ClawHavoc campaign (January-February 2026) infiltrated over 1,200 malicious skills into the OpenClaw marketplace, while MalTool catalogued 6,487 malicious tools that evade conventional detection. In response, twelve reactive security tools emerged, yet all rely on heuristic methods that provide no formal guarantees. We present SkillFortify, the first formal analysis framework for agent skill supply chains, with six contributions: (1) the DY-Skill attacker model, a Dolev-Yao adaptation to the five-phase skill lifecycle with a maximality proof; (2) a sound static analysis framework grounded in abstract interpretation; (3) capability-based sandboxing with a confinement proof; (4) an Agent Dependency Graph with SAT-based resolution and lockfile semantics; (5) a trust score algebra with formal monotonicity; and (6) SkillFortifyBench, a 540-skill benchmark. SkillFortify achieves 96.95% F1 (95% CI: [95.1%, 98.4%]) with 100% precision and 0% false positive rate on 540 skills, while SAT-based resolution handles 1,000-node graphs in under 100 ms.

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it. Skills are grouped offline by category and rendered with interaction history into a compact visual context, teaching he model tool invocation and multi-turn task completion. A Dynamic Curriculum then evaluates each skill file's on-policy helpfulness, retaining only those from which the current policy still benefits within a linearly decaying budget, until the agent operates in a fully zero-shot setting. Extensive agentic experiments demonstrate that SKILL0 achieves substantial improvements over the standard RL baseline (+9.7\% for ALFWorld and +6.6\% for Search-QA), while maintaining a highly efficient context of fewer than 0.5k tokens per step. Our code is available at https://github.com/ZJU-REAL/SkillZero.

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what types are available, how users adopt them, and what risks they pose. To answer these questions, we conduct a large-scale, data-driven analysis of 40,285 publicly listed skills from a major marketplace. Our results show that skill publication tends to occur in short bursts that track shifts in community attention. We also find that skill content is highly concentrated in software engineering workflows, while information retrieval and content creation account for a substantial share of adoption. Beyond content trends, we uncover a pronounced supply-demand imbalance across categories, and we show that most skills remain within typical prompt budgets despite a heavy-tailed length distribution. Finally, we observe strong ecosystem homogeneity, with widespread intent-level redundancy, and we identify non-trivial safety risks, including skills that enable state-changing or system-level actions. Overall, our findings provide a quantitative snapshot of agent skills as an emerging infrastructure layer for agents and inform future work on skill reuse, standardization, and safety-aware design.

Rapid advancements in large language models (LLMs) have revitalized in LLM-based agents, exhibiting impressive human-like behaviors and cooperative capabilities in various scenarios. However, these agents also bring some exclusive risks, stemming from the complexity of interaction environments and the usability of tools. This paper delves into the safety of LLM-based agents from three perspectives: agent quantity, role definition, and attack level. Specifically, we initially propose to employ a template-based attack strategy on LLM-based agents to find the influence of agent quantity. In addition, to address interaction environment and role specificity issues, we introduce Evil Geniuses (EG), an effective attack method that autonomously generates prompts related to the original role to examine the impact across various role definitions and attack levels. EG leverages Red-Blue exercises, significantly improving the generated prompt aggressiveness and similarity to original roles. Our evaluations on CAMEL, Metagpt and ChatDev based on GPT-3.5 and GPT-4, demonstrate high success rates. Extensive evaluation and discussion reveal that these agents are less robust, prone to more harmful behaviors, and capable of generating stealthier content than LLMs, highlighting significant safety challenges and guiding future research. Our code is available at https://github.com/T1aNS1R/Evil-Geniuses.

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code exemplify a broader shift from passive response generation to action-oriented task execution. Yet as agents move toward open-ended, real-world deployment, relying on from-scratch reasoning and low-level tool calls for every task become increasingly inefficient, error-prone, and hard to maintain. This survey examines this challenge through the lens of agent skills, which we define as reusable procedural artifacts that coordinate tools, memory, and runtime context under task-specific constraints. Under this view, agents and skills play complementary roles: agents handle high-level reasoning and planning, while skills form the operational layer that enables reliable, reusable, and composable execution. Skills are therefore central to the scalability, robustness, and maintainability of modern agent systems. We organize the literature around four stages of the agent skill lifecycle -- representation, acquisition, retrieval, and evolution -- and review representative methods, ecosystem resources, and application settings across each stage. We conclude by discussing open challenges in quality control, interoperability, safe updating, and long-term capability management. All related resources, including research papers, open-source data, and projects, are collected for the community in blue{https://github.com/JayLZhou/Awesome-Agent-Skills}.

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on procedures. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills from collection and recommendation to evolution. SkillsVote profiles a million-scale open-source corpus for environment requirements, quality, and verifiability, then synthesizes tasks for verifiable skills. Before execution, SkillsVote performs agentic library search over structured skill library to expose instructional skill context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill use, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. In our evaluation, offline evolution improves GPT-5.2 on Terminal-Bench 2.0 by up to 7.9 pp, while online evolution improves SWE-Bench Pro by up to 2.6 pp. Overall, governed external skill libraries can improve frozen agents without model updates when systems control exposure, credit, and preservation.

Computer-Using Agents (CUAs) aim to autonomously operate computer systems to complete real-world tasks. However, existing agentic systems remain difficult to scale and lag behind human performance. A key limitation is the absence of reusable and structured skill abstractions that capture how humans interact with graphical user interfaces and how to leverage these skills. We introduce CUA-Skill, a computer-using agentic skill base that encodes human computer-use knowledge as skills coupled with parameterized execution and composition graphs. CUA-Skill is a large-scale library of carefully engineered skills spanning common Windows applications, serving as a practical infrastructure and tool substrate for scalable, reliable agent development. Built upon this skill base, we construct CUA-Skill Agent, an end-to-end computer-using agent that supports dynamic skill retrieval, argument instantiation, and memory-aware failure recovery. Our results demonstrate that CUA-Skill substantially improves execution success rates and robustness on challenging end-to-end agent benchmarks, establishing a strong foundation for future computer-using agent development. On WindowsAgentArena, CUA-Skill Agent achieves state-of-the-art 57.5% (best of three) successful rate while being significantly more efficient than prior and concurrent approaches. The project page is available at https://microsoft.github.io/cua_skill/.

Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, current skill construction methods treat the problem as one-shot extraction, overlooking a fundamental tension: a skill tailored to the specific task fails to transfer, while the abstracted skill often provides insufficient guidance. We attribute this fragility to the absence of explicit mechanisms for skill specification and generalization. To address this gap, we introduce SkillComposer, a framework that decomposes skill construction into three learnable operations: create, improve, and merge. Trained via systematic rejection sampling recipe, SkillComposer enables language models to self-evolve skills at inference time and supports three deployment modes: offline for building generalized libraries, online for task-specific refinement, and hybrid for combining both. Comprehensive experiments on τ^2-Bench, LiveCodeBench v6, and AppWorld show that SkillComposer consistently outperforms baselines. Our SkillComposer-4B improves a 27B executor by up to +4.5 on agent tasks and +3.4 on code tasks, while generalizing across domains and task types unseen during training. Analysis reveals that merge and improve address orthogonal quality dimensions and that skill composition is a transferable meta-ability, providing a practical recipe for skill-augmented inference.

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute numerous malicious tasks even without being attacked, indicating a deficiency in agentic use safety alignment during the post-training phase. To address this gap, we propose AgentAlign, a novel framework that leverages abstract behavior chains as a medium for safety alignment data synthesis. By instantiating these behavior chains in simulated environments with diverse tool instances, our framework enables the generation of highly authentic and executable instructions while capturing complex multi-step dynamics. The framework further ensures model utility by proportionally synthesizing benign instructions through non-malicious interpretations of behavior chains, precisely calibrating the boundary between helpfulness and harmlessness. Evaluation results on AgentHarm demonstrate that fine-tuning three families of open-source models using our method substantially improves their safety (35.8% to 79.5% improvement) while minimally impacting or even positively enhancing their helpfulness, outperforming various prompting methods. The dataset and code have both been open-sourced.

LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with environments. Current agents typically utilize a memory module or a retrieval-augmented generation (RAG) mechanism, retrieving past knowledge and instances with similar embeddings from knowledge bases to inform task planning and execution. However, the reliance on unverified knowledge bases raises significant concerns about their safety and trustworthiness. To uncover such vulnerabilities, we propose a novel red teaming approach AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. In particular, we form the trigger generation process as a constrained optimization to optimize backdoor triggers by mapping the triggered instances to a unique embedding space, so as to ensure that whenever a user instruction contains the optimized backdoor trigger, the malicious demonstrations are retrieved from the poisoned memory or knowledge base with high probability. In the meantime, benign instructions without the trigger will still maintain normal performance. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning, and the optimized backdoor trigger exhibits superior transferability, in-context coherence, and stealthiness. Extensive experiments demonstrate AgentPoison's effectiveness in attacking three types of real-world LLM agents: RAG-based autonomous driving agent, knowledge-intensive QA agent, and healthcare EHRAgent. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance (less than 1%) with a poison rate less than 0.1%.

Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks. The rapid capability enhancement of open-source models deployable on consumer-grade GPUs presents a compelling opportunity to drastically reduce these costs by leveraging skill-based behavioral constraints. Nevertheless, automatically generating effective skills tailored specifically for such compact models remains a significant practical challenge. To address this, we propose SKILLER, a natural-language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model agent system as the environment, and propagates all reinforcement learning signals entirely via natural language. Extensive experimental evaluations across five relevant benchmarks using Qwen3.5-9B and Qwen3.5-4B demonstrate that SKILLER outperforms three open-source and one closed-source skill generation or evolution methods, achieving absolute gains ranging from 4.3 to 20.4 percentage points for the 9B model and 1.8 to 13.3 points for the 4B model, while remarkably matching the performance of strong closed-source models on single-skill tasks in SkillsBench. The project is available at https://github.com/DANG-ai/SKILLER.

Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for complex tasks such as web shopping, automated email replies, and financial trading. However, these advancements amplify the risks of adversarial attacks, especially when agents can access sensitive external functionalities. Nevertheless, manipulating LLM agents into performing targeted malicious actions or invoking specific tools remains challenging, as these agents extensively reason or plan before executing final actions. In this work, we present UDora, a unified red teaming framework designed for LLM agents that dynamically hijacks the agent's reasoning processes to compel malicious behavior. Specifically, UDora first generates the model's reasoning trace for the given task, then automatically identifies optimal points within this trace to insert targeted perturbations. The resulting perturbed reasoning is then used as a surrogate response for optimization. By iteratively applying this process, the LLM agent will then be induced to undertake designated malicious actions or to invoke specific malicious tools. Our approach demonstrates superior effectiveness compared to existing methods across three LLM agent datasets. The code is available at https://github.com/AI-secure/UDora.

Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specifications with metadata and optional references, scripts, assets, hooks, package manifests, tests, and companion interfaces. Existing studies explain how Skills are specified, executed, maintained, and evolved, but lack an ontology that defines these artifacts as independent software objects. This paper introduces Skillware as the software abstraction that extends software engineering to persistent Behavioral Artifacts in agent systems. A Skill Artifact specifies reusable task behavior; a Skillware Unit manages that artifact as software through an independent identity and lifecycle. A compatible Agent Host activates the unit for runtime interpretation. Three necessary conditions operationalize category membership: behavioral primacy, independent software identity, and an Agent Host execution relationship. Lifecycle Continuity records whether the same unit identity persists through update, maintenance, rollback, and removal as a separate software-grade property. Evidence combines the Agent Skills specification, a frozen corpus of 138,133 content-deduplicated SKILL.md records associated with 20,556 repository identifiers, independent empirical studies, 15 category-boundary cases, and 13 fixed-revision engineering implementations. The evidence establishes a recurring artifact envelope, separable software identities, compatible execution paths, and lifecycle engineering pressure. Skillware provides the software ontology and engineering lifecycle through which agent capabilities can become identifiable, composable, maintainable, and evolvable software artifacts.

Agent skills have become an important mechanism for equipping language-model agents with reusable procedural knowledge. However, providing skills alone does not guarantee that current models can effectively identify, apply, and coordinate them. To improve skill-use capabilities, we introduce SKT, a verified data synthesis pipeline that constructs skill-grounded tasks and executable trajectories from large collections of agent skills. SKT selects suitable single-skill and multi-skill configurations, synthesizes tasks through rule-based and agent-based verification with feedback-guided repair, and retains only successful trajectories that substantially use every required skill. Using 2,000 public skills, SKT produces 4,000 task packages and 27,164 verified trajectories. Based on the same pipeline and a disjoint test pool, we further construct SkillEval, a held-out executable benchmark for evaluating skill use. Experiments across diverse models, benchmarks, and agent harnesses show that supervised fine-tuning on SKT-generated trajectories consistently improves skill-use performance. Verification ablations, cross-harness evaluation, and scaling experiments further demonstrate that these gains depend on high-quality supervision, extend beyond a single agent interface, and increase with broader skill coverage. Together, these results establish verified data synthesis as an effective and scalable approach for skill-use training.

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a multi-agent framework that synthesizes a single auditable skill from trajectories generated by a base agent. The output is a human-readable artifact that can be inspected before use. Rather than merely summarizing trajectories, SkillGen leverages contrastive induction over both successful and failed trajectories to identify reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures. SkillGen then generates candidate skills and iteratively refines the skill. A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance. Specifically, we compare outcomes on the same instances with and without the skill, so that we account for both repairs (cases where the skill fixes a baseline failure) and regressions (cases where the skill breaks a baseline success). Across a broad range of agents and datasets, SkillGen consistently improves held-out performance, outperforms existing skill-generation baselines, and produces skills that transfer across models.

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization.

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example, a well-built agent using GPT-3.5-Turbo as its core can outperform the more advanced GPT-4 model by leveraging external components. More importantly, the usage of tools enables these systems to perform actions in the real world, moving from merely generating text to actively interacting with their environment. Given the agents' practical applications and their ability to execute consequential actions, it is crucial to assess potential vulnerabilities. Such autonomous systems can cause more severe damage than a standalone language model if compromised. While some existing research has explored harmful actions by LLM agents, our study approaches the vulnerability from a different perspective. We introduce a new type of attack that causes malfunctions by misleading the agent into executing repetitive or irrelevant actions. We conduct comprehensive evaluations using various attack methods, surfaces, and properties to pinpoint areas of susceptibility. Our experiments reveal that these attacks can induce failure rates exceeding 80\% in multiple scenarios. Through attacks on implemented and deployable agents in multi-agent scenarios, we accentuate the realistic risks associated with these vulnerabilities. To mitigate such attacks, we propose self-examination detection methods. However, our findings indicate these attacks are difficult to detect effectively using LLMs alone, highlighting the substantial risks associated with this vulnerability.

Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during interaction. Recent approaches address this challenge by learning reusable skills from successful trajectories. However, these skill learning methods largely assume static and safe environments, overlooking risks from adversarial interactions (e.g., prompt injections) and environmental dynamics (e.g., pop-ups). In dynamic settings, such assumptions can lead to risky skill learning and brittle execution, undermining the reliability of CUAs. This raises the question: how can CUAs learn and use skills safely in dynamic environments? To address this problem, we propose SkillHarness, a framework for safe skill harnessing in dynamic environments. SkillHarness moves beyond static skill abstractions by modeling skill learning and utilization as a safety-constrained interaction process. Specifically, we introduce the skill boundary that leverages multi-source supervision signals to identify safe skills from interaction trajectories, and construct self-improving safety constraints throughout the skill lifecycle. In addition, SkillHarness introduces selective skill reuse, where tasks are guided to decompose according to context and completed through the selective activation of skill subsets. Our experiments demonstrate that SkillHarness significantly reduces the unsafe rate of learned skills by 57.1% and consistently improves execution stability under dynamic environmental changes, outperforming existing baselines.

The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill selection, orchestration, and ecosystem-level management. AgentSkillOS comprises two stages: (i) Manage Skills, which organizes skills into a capability tree via node-level recursive categorization for efficient discovery; and (ii) Solve Tasks, which retrieves, orchestrates, and executes multiple skills through DAG-based pipelines. To evaluate the agent's ability to invoke skills, we construct a benchmark of 30 artifact-rich tasks across five categories: data computation, document creation, motion video, visual design, and web interaction. We assess the quality of task outputs using LLM-based pairwise evaluation, and the results are aggregated via a Bradley-Terry model to produce unified quality scores. Experiments across three skill ecosystem scales (200 to 200K skills) show that tree-based retrieval effectively approximates oracle skill selection, and that DAG-based orchestration substantially outperforms native flat invocation even when given the identical skill set. Our findings confirm that structured composition is the key to unlocking skill potential. Our GitHub repository is available at:https://github.com/ynulihao/AgentSkillOS.

Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse. Existing vetting usually evaluates each skill in isolation, while real agent tasks often invoke multiple skills in a shared execution context. This creates Skill Composition Risk (SCR): a skill that appears benign alone can become harmful when its outputs, trust signals, authorization cues, or side effects influence later invocations along an activated path. We introduce SCR-Bench to evaluate this risk in controlled, sandboxed skill environments. Rather than relying only on textual intent or surface behavior, SCR-Bench records downstream state changes and path-level outcomes across composed skill executions. It contains three sub-benchmarks: SCR-CapFlow for capability-flow composition, SCR-TrustLift for trust-transfer composition, and SCR-AuthBlur for authorization-confusion composition. Across SCR-Bench, composed paths expose risks that are largely absent under isolated evaluation. In SCR-CapFlow, attack success rate reaches 33.6 percent under composition, compared with near-zero isolated baselines. In SCR-TrustLift, attack success rate exceeds 96.5 percent on four of five backends. In SCR-AuthBlur, the risky-approval rate increases by 71.8 percent relative to the L0 isolated baseline under the L1 context setting. These results show that agent skill security should be assessed at the level of activated paths rather than isolated artifacts. SCR and SCR-Bench provide a foundation for path-aware risk evaluation and defense in LLM agent skill ecosystems. Benchmark: https://github.com/saint-viperx/SCR_Bench.

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a distinct safety challenge in that harmful behavior may emerge through sequences of individually plausible steps, including intermediate actions that appear locally acceptable but collectively lead to unauthorized actions. We present AgentHazard, a benchmark for evaluating harmful behavior in computer-use agents. AgentHazard contains 2,653 instances spanning diverse risk categories and attack strategies. Each instance pairs a harmful objective with a sequence of operational steps that are locally legitimate but jointly induce unsafe behavior. The benchmark evaluates whether agents can recognize and interrupt harm arising from accumulated context, repeated tool use, intermediate actions, and dependencies across steps. We evaluate AgentHazard on Claude Code, OpenClaw, and IFlow using mostly open or openly deployable models from the Qwen3, Kimi, GLM, and DeepSeek families. Our experimental results indicate that current systems remain highly vulnerable. In particular, when powered by Qwen3-Coder, Claude Code exhibits an attack success rate of 73.63\%, suggesting that model alignment alone does not reliably guarantee the safety of autonomous agents.

The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice. Rather than encoding all procedural knowledge within model weights, agent skills -- composable packages of instructions, code, and resources that agents load on demand -- enable dynamic capability extension without retraining. It is formalized in a paradigm of progressive disclosure, portable skill definitions, and integration with the Model Context Protocol (MCP). This survey provides a comprehensive treatment of the agent skills landscape, as it has rapidly evolved during the last few months. We organize the field along four axes: (i) architectural foundations, examining the SKILL.md specification, progressive context loading, and the complementary roles of skills and MCP; (ii) skill acquisition, covering reinforcement learning with skill libraries, autonomous skill discovery (SEAgent), and compositional skill synthesis; (iii) deployment at scale, including the computer-use agent (CUA) stack, GUI grounding advances, and benchmark progress on OSWorld and SWE-bench; and (iv) security, where recent empirical analyses reveal that 26.1% of community-contributed skills contain vulnerabilities, motivating our proposed Skill Trust and Lifecycle Governance Framework -- a four-tier, gate-based permission model that maps skill provenance to graduated deployment capabilities. We identify seven open challenges -- from cross-platform skill portability to capability-based permission models -- and propose a research agenda for realizing trustworthy, self-improving skill ecosystems. Unlike prior surveys that broadly cover LLM agents or tool use, this work focuses specifically on the emerging skill abstraction layer and its implications for the next generation of agentic systems. Project repo: https://github.com/scienceaix/agentskills

Agent skills, SKILL.md files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL.md ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code will be released upon acceptance.

Unsupervised skill discovery drives intelligent agents to explore the unknown environment without task-specific reward signal, and the agents acquire various skills which may be useful when the agents adapt to new tasks. In this paper, we propose "Multi-agent Skill Discovery"(MASD), a method for discovering skills for coordination patterns of multiple agents. The proposed method aims to maximize the mutual information between a latent code Z representing skills and the combination of the states of all agents. Meanwhile it suppresses the empowerment of Z on the state of any single agent by adversarial training. In another word, it sets an information bottleneck to avoid empowerment degeneracy. First we show the emergence of various skills on the level of coordination in a general particle multi-agent environment. Second, we reveal that the "bottleneck" prevents skills from collapsing to a single agent and enhances the diversity of learned skills. Finally, we show the pretrained policies have better performance on supervised RL tasks.

Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBench study, Progressive Disclosure changes runtime behavior before aggregate outcomes: distinct Skill resources touched per trajectory rise from 1.18 to 3.85, and effective uptake events rise from 1.33 to 3.92. It also yields 17 additional verifier-passing trials out of 410 matched trials (+4.1%) over the normalized flat baseline. The benefit is task-dependent. Progressive Disclosure helps when supporting resources guide implementation, checking, or repair, but is weaker when success hinges on exact output conventions, numerical thresholds, or long artifact-generation pipelines. These results show that Skill organization is not mere presentation: it can change how agents search and apply procedural knowledge, while outcome gains depend on whether the exposed resources are actionable for the task. Code is available at https://github.com/zhiyuchen-ai/skill-juror.

An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent loads the skill when it judges that a task matches the skill description. Anthropic introduced the format in October 2025 as an open specification. Nine months later, we find that skill files in the millions sit in public GitHub repositories. Skills are unlike the artifacts the SE research community usually mines: they are written mainly in natural language, a model selects them probabilistically at run time, and no compiler or type checker verifies the selection. They also have no central registry or package manager, so they spread by copying folders between repositories. How developers write, reuse, and maintain skills is therefore an empirical question, and no existing dataset records this population. We present GitSkills, a dataset of 3,797,117 SKILL.md files collected from 282,200 public repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. It groups identical files into 1,877,981 distinct contents and enriches one representative per group with the full text, parsed front matter, folder contents, repository metadata, and, for a subset, the commit history of the file. A single self- contained SQLite file supports research on the adoption, reuse, structure, authorship, maintenance, and security of agent skills.

As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security risks. However, relevant studies on web agent attacks remain limited. Existing red-teaming approaches mainly rely on manually crafted attack strategies or static models trained offline. Such methods fail to capture the underlying behavioral patterns of web agents, making it difficult to generalize across diverse environments. In web agent attacks, success requires the continuous discovery and evolution of attack strategies. To this end, we propose Genesis, a novel agentic framework composed of three modules: Attacker, Scorer, and Strategist. The Attacker generates adversarial injections by integrating the genetic algorithm with a hybrid strategy representation. The Scorer evaluates the target web agent's responses to provide feedback. The Strategist dynamically uncovers effective strategies from interaction logs and compiles them into a continuously growing strategy library, which is then re-deployed to enhance the Attacker's effectiveness. Extensive experiments across various web tasks show that our framework discovers novel strategies and consistently outperforms existing attack baselines.

Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through agent skills: reusable workflows, and code, that augment agents with domain-specific capabilities. Most skills today are hand-crafted, and existing evolutionary approaches optimize low-level artifacts (e.g. prompts \& code) that are tightly coupled to specific models and tasks. We introduce EvoSkill, a self-evolving framework that automatically discovers and refines agent skills through iterative failure analysis. EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders. A Pareto frontier of agent programs governs selection, retaining only skills that improve held-out validation performance while the underlying model remains frozen. We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S.\ Treasury data, where it improves exact-match accuracy by 7.3\% (60.6\% to 67.9\%); and SealQA, a search-augmented QA benchmark with noisy retrieval, where it yields a 12.1\% gain (26.6\% to 38.7\%). We also investigate the zero-shot transfer capabilties of skills evolved on one task to the other; in particular: skills evolved from SealQA transfers zero-shot to BrowseComp, improving accuracy by 5.3\% without modification demonstrating that skill-level optimization produces transferable capabilities beyond the training task.

Agent skills extend LLM agents with reusable procedures, tools, and domain-specific workflows, but their safety depends on resolving dependencies among interacting instructions. We introduce SkillLogic, a framework for analyzing logical relations in skill files and constructing executable tests from them. Our taxonomy covers eight relation types, including preconditions that gate valid actions, constraints that limit how allowed actions may be performed, and fallbacks that specify recovery behavior after failure. Using SkillLogic, we scan over 5000 public skills and find that 70% contain at least one logical relation. We then construct SLBench, an 86-case executable benchmark from high-confidence, high-impact, and locally testable relations. Evaluating Codex and Claude Code across six LLM backbones shows unsafe rates up to 70%, with violations leading to privacy leaks, unsafe configuration changes, and incomplete cleanup. The human audit attributes failures to both agent capability gaps and low-salience skill text. We further show that SLGuard, a lightweight inference-time scaffold, reduces violations by 63% on targeted cases. Our results establish logical-relation following as a distinct reliability challenge for skill-guided agents.

AI agents that autonomously interact with external tools and environments show great promise across real-world applications. However, the external data which agent consumes also leads to the risk of indirect prompt injection attacks, where malicious instructions embedded in third-party content hijack agent behavior. Guided by benchmarks, such as AgentDojo, there has been significant amount of progress in developing defense against the said attacks. As the technology continues to mature, and that agents are increasingly being relied upon for more complex tasks, there is increasing pressing need to also evolve the benchmark to reflect threat landscape faced by emerging agentic systems. In this work, we reveal three fundamental flaws in current benchmarks and push the frontier along these dimensions: (i) lack of dynamic open-ended tasks, (ii) lack of helpful instructions, and (iii) simplistic user tasks. To bridge this gap, we introduce AgentDyn, a manually designed benchmark featuring 60 challenging open-ended tasks and 560 injection test cases across Shopping, GitHub, and Daily Life. Unlike prior static benchmarks, AgentDyn requires dynamic planning and incorporates helpful third-party instructions. Our evaluation of ten state-of-the-art defenses suggests that almost all existing defenses are either not secure enough or suffer from significant over-defense, revealing that existing defenses are still far from real-world deployment. Our benchmark is available at https://github.com/leolee99/AgentDyn.

As LLM agent ecosystems grow, the number of available skills (tools, plugins) has reached tens of thousands, making it infeasible to inject all skills into an agent's context. This creates a need for skill routing -- retrieving the most relevant skills from a large pool given a user task. The problem is compounded by pervasive functional overlap in community skill repositories, where many skills share similar names and purposes yet differ in implementation details. Despite its practical importance, skill routing remains under-explored. Current agent architectures adopt a progressive disclosure design -- exposing only skill names and descriptions to the agent while keeping the full implementation body hidden -- implicitly treating metadata as sufficient for selection. We challenge this assumption through a systematic empirical study on a benchmark of ~$80K skills and 75 expert-verified queries. Our key finding is that the skill body (full implementation text) is the decisive signal: removing it causes 29--44 percentage point degradation across all retrieval methods, and cross-encoder attention analysis reveals 91.7% of attention concentrating on the body field. Motivated by this finding, we propose SkillRouter, a two-stage retrieve-and-rerank pipeline totaling only 1.2B parameters (0.6B encoder + 0.6B reranker). SkillRouter achieves 74.0% top-1 routing accuracy and delivers the strongest average result among the compact and zero-shot baselines we evaluate, while remaining deployable on consumer hardware.

While real-world applications of reinforcement learning are becoming popular, the security and robustness of RL systems are worthy of more attention and exploration. In particular, recent works have revealed that, in a multi-agent RL environment, backdoor trigger actions can be injected into a victim agent (a.k.a. Trojan agent), which can result in a catastrophic failure as soon as it sees the backdoor trigger action. To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in a multi-agent competitive reinforcement learning system, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their Trojan behavior. In order to solve this problem, we propose PolicyCleanse that is based on the property that the activated Trojan agents accumulated rewards degrade noticeably after several timesteps. Along with PolicyCleanse, we also design a machine unlearning-based approach that can effectively mitigate the detected backdoor. Extensive experiments demonstrate that the proposed methods can accurately detect Trojan agents, and outperform existing backdoor mitigation baseline approaches by at least 3% in winning rate across various types of agents and environments.

Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge. Reusable agent skills, which encapsulate successful problem-solving strategies, offer a natural remedy by enabling agents to build on prior experience. However, curating such skills has largely remained a manual endeavor, requiring human experts to distill rich domain knowledge into actionable guidelines. In this work, we present Multi-agent INduction and Deduction for Skills (MIND-Skill), a framework that automatically induces generalizable skills from successful trajectories with robust quality guarantees. MIND-Skill consists of an induction agent which is tasked to abstract reusable skills from successful trajectories, and a deduction agent which aims to reconstruct trajectories by following the induced skills. To guarantee the quality of the generated skills, we introduce a reconstruction loss that compares input and reconstructed trajectories, an outcome loss that enforces the correctness of the reconstructed trajectories, and a rubric loss that assesses the documentation quality and regularizes the abstraction level of the generated skills according to predefined criteria. These textual losses are jointly optimized with TextGrad, and the resulting skills are evaluated on held-out tasks unseen during optimization. Experiments on AppWorld and BFCL-v3 show that MIND-Skill consistently outperforms concurrent skill generation methods.

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is https://github.com/Cassie07/AgentSkill_Survey

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using LLM-to-LLM interactions within a text-based RPG where parameterized behavioral profiles (9 alignments x 4 motivations, yielding 36 profiles with explicit ethical ground truth) serve as our experimental testbed. Unlike accidental deception from misalignment, we investigate a two-stage system that infers target agent characteristics and generates deceptive responses steering targets toward actions counter to their beliefs and motivations. We find that deceptive intervention produces differential effects concentrated in specific behavioral profiles rather than distributed uniformly, and that 88.5% of successful deceptions employ misdirection (true statements with strategic framing) rather than fabrication, indicating fact-checking defenses would miss the large majority of adversarial responses. Motivation, inferable at 98%+ accuracy, serves as the primary attack vector, while belief systems remain harder to identify (49% inference ceiling) or exploit. These findings identify which agent profiles require additional safeguards and suggest that current fact-verification approaches are insufficient against strategically framed deception.

Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually change. Existing methods improve skills in bounded runs and retain only the final artifact, discarding the decision history that later agents need to interpret prior revisions, evaluations, and rejected alternatives. We introduce SkillHone, a harness for continual agent skill evolution grounded in persistent decision history. SkillHone pairs skill revisions with evaluation-side evidence that supplies practice feedback, recording structured histories of diagnoses, revisions, evidence, and outcomes. Role-separated subagents run candidate skills on practice probes with redacted reporting and propose revisions informed by prior decisions, enabling cross-session refinement without rediscovering past rationale. On deep-research benchmarks, SkillHone runs without a pre-integrated search stack and outperforms the commercially backed deep-research agent by 15.8 points on GAIA and 3.2 points on WebWalkerQA-EN, while also exceeding prior skill-evolution methods. We further deploy SkillHone on internal tool-mediated analysis scenarios, where it improves accuracy by an average of 18.8 points across seven settings.

Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and implicitly assumes human executors, making it difficult to use directly as the skills required by agents. To bridge the gap between human-oriented guides and agent-executable skills, we formalize this problem as guide-to-skill learning: converting in-the-wild guides into executable skills and continuously improving them from trajectories observable to the agent. To evaluate the capability of existing agents on this task, we introduce MMG2Skill-Bench, the first benchmark designed for this problem. We further propose MMG2Skill, a closed-loop framework that compiles guides into editable skills, conditions a fixed vision-language model (VLM) agent on these skills during execution, and revises the skills from trajectory-level root-cause feedback without using benchmark scores. Across GUI control, open-ended gameplay, and strategic card play with six VLM backbones, MMG2Skill consistently outperforms vanilla baseline agents in every model-domain setting, achieving macro-average gains of +12.8 to +25.3 percentage points across backbones. Ablation studies show that directly prompting agents with raw guides can degrade performance, while both structured skill construction and trajectory-driven revision are necessary for the observed improvements. On success-inferable tasks, analyzer-based early stopping further prevents late-stage performance regressions and saves 25%-53% of attempts when the success signal is properly calibrated.

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use difficult. Final verifier success is too coarse for both evaluation and training, since an agent may pass through trial and error while selecting distractor skills, skipping required steps, composing workflows incorrectly or omitting final checks. We introduce SkillCoach, a self-evolving rubric framework for evaluating and enhancing agentic skill-use. SkillCoach derives skill-grounded process rubrics from real rollouts and evaluates trajectories along four dimensions: skill selection, skill following, skill composition, and skill-grounded reflection. It keeps the external verifier as a separate outcome signal, allowing process quality to be distinguished from accidental task success. The evolved rubrics further serve as process supervision for selecting high-quality training trajectories. Experiments show that evolved rubrics substantially improve evaluation quality, expose failures hidden by final accuracy, and provide stronger supervision signals than outcome-only filtering for enhancing agentic skill-use.

Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does greater autonomy invite greater risk? We introduce ANCHOR, an automated auditing framework that stress-tests CLI agents on illegal tasks grounded in public US court cases. ANCHOR deploys an auditor agent fine-tuned on dark personality data using supervised and reinforcement fine tuning. This auditor roleplays persistent malicious users who decompose tasks, reframe requests upon refusal, and adapt strategies across multi-turn interactions. Evaluating frontier CLI agents, we find that while they often refuse illegal tasks when prompted directly, compliance reaches 100\% under persistent malicious interaction. When agents comply, they frequently exceed user requests, autonomously building infrastructure for large-scale harm, including catastrophic risk scenarios such as large-scale financial fraud and bioweapon development. These findings demonstrate that current alignment techniques are insufficient for autonomous agents and underscore the need for safety evaluations against persistent, adaptive malicious users. We release ANCHOR at https://github.com/garified/anchor

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building such person-grounded agents remains difficult because actionable knowledge associated with a person or role is usually embedded in heterogeneous traces rather than written as clean instructions. Existing memory and persona systems capture fragments of this evidence, while skill frameworks provide portable packaging formats; however, there is no end-to-end workflow for distilling these traces into inspectable, correctable, and agent-usable skills. We present an automated trace-to-skill distillation system for generating person-grounded AI skills via expert knowledge distillation. Given materials from a target person or role, COLLEAGUE.SKILL produces a versioned skill package with two coordinated tracks: a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. The package can be inspected, invoked, updated through natural-language feedback, rolled back, installed across agent hosts, and optionally prepared for controlled distribution. We describe the artifact contract, generation workflow, correction lifecycle, deployment surface, and domain presets implemented in the open-source system. At the time of writing, the public repository has approximately 18.5k GitHub stars; the gallery lists 215 skills from 165 contributors and more than 100k cumulative stars across listed skill cards. The system illustrates how person-grounded skills can be represented as portable, correctable packages rather than opaque prompts or hidden memories.

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security implications of these LLM-based multi-agent systems have not been thoroughly investigated, particularly concerning the spread of manipulated knowledge. In this paper, we investigate this critical issue by constructing a detailed threat model and a comprehensive simulation environment that mirrors real-world multi-agent deployments in a trusted platform. Subsequently, we propose a novel two-stage attack method involving Persuasiveness Injection and Manipulated Knowledge Injection to systematically explore the potential for manipulated knowledge (i.e., counterfactual and toxic knowledge) spread without explicit prompt manipulation. Our method leverages the inherent vulnerabilities of LLMs in handling world knowledge, which can be exploited by attackers to unconsciously spread fabricated information. Through extensive experiments, we demonstrate that our attack method can successfully induce LLM-based agents to spread both counterfactual and toxic knowledge without degrading their foundational capabilities during agent communication. Furthermore, we show that these manipulations can persist through popular retrieval-augmented generation frameworks, where several benign agents store and retrieve manipulated chat histories for future interactions. This persistence indicates that even after the interaction has ended, the benign agents may continue to be influenced by manipulated knowledge. Our findings reveal significant security risks in LLM-based multi-agent systems, emphasizing the imperative need for robust defenses against manipulated knowledge spread, such as introducing ``guardian'' agents and advanced fact-checking tools.

The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these powerful features also introduce a critical security risk: indirect prompt injection, a sophisticated attack vector that compromises the core of these agents, the LLM, by manipulating contextual information rather than direct user prompts. In this work, we propose a generic black-box fuzzing framework, AgentVigil, designed to automatically discover and exploit indirect prompt injection vulnerabilities across diverse LLM agents. Our approach starts by constructing a high-quality initial seed corpus, then employs a seed selection algorithm based on Monte Carlo Tree Search (MCTS) to iteratively refine inputs, thereby maximizing the likelihood of uncovering agent weaknesses. We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o, respectively, nearly doubling the performance of baseline attacks. Moreover, AgentVigil exhibits strong transferability across unseen tasks and internal LLMs, as well as promising results against defenses. Beyond benchmark evaluations, we apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents. Our benchmark is available here: https://safearena.github.io

As AI systems increasingly assume roles where trust and alignment with human values are essential, understanding when and why they engage in deception has become a critical research priority. We introduce The Traitors, a multi-agent simulation framework inspired by social deduction games, designed to probe deception, trust formation, and strategic communication among large language model (LLM) agents under asymmetric information. A minority of agents the traitors seek to mislead the majority, while the faithful must infer hidden identities through dialogue and reasoning. Our contributions are: (1) we ground the environment in formal frameworks from game theory, behavioral economics, and social cognition; (2) we develop a suite of evaluation metrics capturing deception success, trust dynamics, and collective inference quality; (3) we implement a fully autonomous simulation platform where LLMs reason over persistent memory and evolving social dynamics, with support for heterogeneous agent populations, specialized traits, and adaptive behaviors. Our initial experiments across DeepSeek-V3, GPT-4o-mini, and GPT-4o (10 runs per model) reveal a notable asymmetry: advanced models like GPT-4o demonstrate superior deceptive capabilities yet exhibit disproportionate vulnerability to others' falsehoods. This suggests deception skills may scale faster than detection abilities. Overall, The Traitors provides a focused, configurable testbed for investigating LLM behavior in socially nuanced interactions. We position this work as a contribution toward more rigorous research on deception mechanisms, alignment challenges, and the broader social reliability of AI systems.

Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often unreliable, incomplete, or outdated. Existing skill-evolution methods often address these deficiencies through heuristic reflections without an explicit optimization formulation. In this paper, we propose SkillGrad, a gradient-descent-inspired framework for optimizing agent skills. SkillGrad treats the skill package as a structured parameter to optimize in a gradient descent fashion: task executions provide trajectory-level loss evidence, automatic diagnoses then provide text-based gradients that indicate the correction directions. To stabilize optimization across iterations, a momentum agent accumulates recurring diagnostic patterns into a persistent memory overlay. Finally, an LLM-based patcher executes the parameter update by applying layer-aware edits to the skill package. Evaluated on SpreadsheetBench Verified and WikiTableQuestions, SkillGrad consistently outperforms training-based skill evolution baselines across two backbone LLMs, improving over the strongest training-based baseline by 6.7 percentage points on average. Ablations further show that momentum and contrastive diagnosis both contribute to the final skill quality.

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables. Code and data will be available at: https://weibowen555.github.io/ClawSafety/.

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it introduces a critical, unexplored attack surface, i.e., the trust boundary between an agent's reasoning core and its own past. In this paper, we introduce MemoryGraft. It is a novel indirect injection attack that compromises agent behavior not through immediate jailbreaks, but by implanting malicious successful experiences into the agent's long-term memory. Unlike traditional prompt injections that are transient, or standard RAG poisoning that targets factual knowledge, MemoryGraft exploits the agent's semantic imitation heuristic which is the tendency to replicate patterns from retrieved successful tasks. We demonstrate that an attacker who can supply benign ingestion-level artifacts that the agent reads during execution can induce it to construct a poisoned RAG store where a small set of malicious procedure templates is persisted alongside benign experiences. When the agent later encounters semantically similar tasks, union retrieval over lexical and embedding similarity reliably surfaces these grafted memories, and the agent adopts the embedded unsafe patterns, leading to persistent behavioral drift across sessions. We validate MemoryGraft on MetaGPT's DataInterpreter agent with GPT-4o and find that a small number of poisoned records can account for a large fraction of retrieved experiences on benign workloads, turning experience-based self-improvement into a vector for stealthy and durable compromise. To facilitate reproducibility and future research, our code and evaluation data are available at https://github.com/Jacobhhy/Agent-Memory-Poisoning.

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future behavior. In this work, we study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace. We evaluate two agentic systems, Anthropic Claude Code and OpenAI Codex, across four models: Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2, and GPT-5.5. Our results show that although it is difficult to make an agent overwrite its own memory files using untrusted external content, payloads already planted in those files can successfully attack current and future sessions. Attack success and payload persistence vary substantially across systems, models, adversarial goals, and multi-session attack sequences. These findings show that persistent memory changes the threat model for prompt injection and motivate defenses that protect memory updates without removing useful agent adaptation.

Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill ecosystem rapidly expands, it remains unclear how different models and agent frameworks interact with skills, how to evaluate skill quality, and how users should select skills under practical cost-performance trade-offs. In this paper, we present OpenSkillEval, an automatic evaluation framework for both skill-augmented agent systems and the skills themselves. Instead of relying on static benchmarks, OpenSkillEval automatically constructs realistic task instances from evolving real-world artifacts across five categories of downstream applications: presentation generation, front-end web design, poster generation, data visualization, and report generation. It further collects and organizes community-contributed skills for controlled comparison under unified task settings. Using more than 600 dynamically generated task instances and 30 open-source skills, we conduct a systematic evaluation of state-of-the-art models and agent frameworks. Our results show that skill availability does not guarantee effective skill usage, that the benefit of skill augmentation depends strongly on both the underlying model and the agent framework, and that many publicly popular skills do not consistently outperform base agents without skills. These findings highlight the need for dynamic, task-grounded evaluation and provide practical insights into the design, selection, and deployment of skills for LLM agents. Additional cases and benchmark resources are available on the project website: https://yingjiahao14.github.io/OpenSkillEval-Web/.

Learning cooperative multi-agent policy from offline multi-task data that can generalize to unseen tasks with varying numbers of agents and targets is an attractive problem in many scenarios. Although aggregating general behavior patterns among multiple tasks as skills to improve policy transfer is a promising approach, two primary challenges hinder the further advancement of skill learning in offline multi-task MARL. Firstly, extracting general cooperative behaviors from various action sequences as common skills lacks bringing cooperative temporal knowledge into them. Secondly, existing works only involve common skills and can not adaptively choose independent knowledge as task-specific skills in each task for fine-grained action execution. To tackle these challenges, we propose Hierarchical and Separate Skill Discovery (HiSSD), a novel approach for generalizable offline multi-task MARL through skill learning. HiSSD leverages a hierarchical framework that jointly learns common and task-specific skills. The common skills learn cooperative temporal knowledge and enable in-sample exploitation for offline multi-task MARL. The task-specific skills represent the priors of each task and achieve a task-guided fine-grained action execution. To verify the advancement of our method, we conduct experiments on multi-agent MuJoCo and SMAC benchmarks. After training the policy using HiSSD on offline multi-task data, the empirical results show that HiSSD assigns effective cooperative behaviors and obtains superior performance in unseen tasks.

Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext. We present LatentSkill, a framework that converts textual skills into plug-and-play LoRA adapters through a pretrained hypernetwork. LatentSkill stores skill knowledge in weight space rather than context space, removing per-step skill tokens while preserving modular loading, scaling, and composition. On ALFWorld and Search-QA, LatentSkill outperforms the corresponding in-context skill baseline while using substantially fewer prefill tokens: it improves ALFWorld success by 21.4 and 13.4 points on the seen and unseen splits with 64.1% fewer prefill tokens, and improves Search-QA exact match by 3.0 points with 72.2% lower skill-token overhead. Further analysis shows that generated skill LoRAs form a structured semantic geometry, can be precisely controlled via the LoRA scaling coefficient, and can be composed through parameter-space arithmetic when skill components are aligned. These findings suggest that weight-space skills provide an efficient, modular, and less exposed substrate for extending LLM agents.

Modern scientific ecosystems are rich in procedural knowledge across repositories, APIs, scripts, notebooks, documentation, databases, and papers, yet much of this knowledge remains fragmented across heterogeneous artifacts that agents cannot readily operationalize. This gap between abundant scientific know-how and usable agent capabilities is a key bottleneck for building effective scientific agents. We present SkillFoundry, a self-evolving framework that converts such resources into validated agent skills, reusable packages that encode task scope, inputs and outputs, execution steps, environment assumptions, provenance, and tests. SkillFoundry organizes a target domain as a domain knowledge tree, mines resources from high-value branches, extracts operational contracts, compiles them into executable skill packages, and then iteratively expands, repairs, merges, or prunes the resulting library through a closed-loop validation process. SkillFoundry produces a substantially novel and internally valid skill library, with 71.1\% of mined skills differing from existing skill libraries such as SkillHub and SkillSMP. We demonstrate that these mined skills improve coding agent performance on five of the six MoSciBench datasets. We further show that SkillFoundry can design new task-specific skills on demand for concrete scientific objectives, and that the resulting skills substantially improve performance on two challenging genomics tasks: cell type annotation and the scDRS workflow. Together, these results show that automatically mined skills improve agent performance on benchmarks and domain-specific tasks, expand coverage beyond hand-crafted skill libraries, and provide a practical foundation for more capable scientific agents.

The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly complex tasks. However, in this paper, we identify a critical yet previously overlooked security vulnerability in multimodal agents: cross-modal prompt injection attacks. To exploit this vulnerability, we propose CrossInject, a novel attack framework in which attackers embed adversarial perturbations across multiple modalities to align with target malicious content, allowing external instructions to hijack the agent's decision-making process and execute unauthorized tasks. Our approach incorporates two key coordinated components. First, we introduce Visual Latent Alignment, where we optimize adversarial features to the malicious instructions in the visual embedding space based on a text-to-image generative model, ensuring that adversarial images subtly encode cues for malicious task execution. Subsequently, we present Textual Guidance Enhancement, where a large language model is leveraged to construct the black-box defensive system prompt through adversarial meta prompting and generate an malicious textual command that steers the agent's output toward better compliance with attackers' requests. Extensive experiments demonstrate that our method outperforms state-of-the-art attacks, achieving at least a +30.1% increase in attack success rates across diverse tasks. Furthermore, we validate our attack's effectiveness in real-world multimodal autonomous agents, highlighting its potential implications for safety-critical applications.

Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an action-graded harm rubric that scores an agent's tool-call trajectory on a seven-level ordinal scale (L0 to L6) according to whether the executed action was reversible, whether it crossed scope to reach another party, and whether it expanded privilege. We compute the scale two ways: a deterministic oracle that reads the trajectory and the attacker's stated goal, and a panel of three frontier language-model judges that read a tag-free account of the same trajectory. Across four victim models and two defenses on the AgentDojo workspace suite, severity grading exposes three cases the binary metric hides, including a defense that reports a zero attack-success rate while still permitting an externally visible cross-scope leak through an unfiltered tool. The judge panel reproduces the oracle with high ordinal agreement (Krippendorff's alpha = 0.91) but shares systematic blind spots that we characterize, most notably a failure to recognize escalation chains. Unlike prior work that provides harm taxonomies, harmful-task completion tests, execution-level safety benchmarks, or severity-aware simulation, our contribution is a reusable, trace-grounded severity instrument applied to the actual actions recorded in existing red-team logs. All code, prompts, and per-episode logs are released.

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and task-specific skills for dynamic execution. However, existing skill-based reinforcement learning (RL) methods typically force a rigid choice between full externalization, which incurs prohibitive context overhead, and full internalization, which risks overfitting and knowledge conflicts. To address this dilemma, we propose Skill0.5, a novel agentic RL framework that explicitly differentiates skill treatments by combining general skill internalization with task-specific skill utilization. Driven by a dynamic, difficulty-aware router, Skill0.5 streams tasks into distinct mastery tiers to apply tailored optimization strategies: it internalizes general skills via privileged distillation to build a cognitive foundation for hard tasks, while using diagnostic probing on easy tasks to penalize shortcuts and enforce specific skill utilization. Experiments on ALFWorld and WebShop demonstrate that Skill0.5 outperforms both memory-based and skill-based RL baselines, yielding performance improvements across both in-distribution and out-of-distribution scenarios.

In this work, we study the risks of collective financial fraud in large-scale multi-agent systems powered by large language model (LLM) agents. We investigate whether agents can collaborate in fraudulent behaviors, how such collaboration amplifies risks, and what factors influence fraud success. To support this research, we present MultiAgentFraudBench, a large-scale benchmark for simulating financial fraud scenarios based on realistic online interactions. The benchmark covers 28 typical online fraud scenarios, spanning the full fraud lifecycle across both public and private domains. We further analyze key factors affecting fraud success, including interaction depth, activity level, and fine-grained collaboration failure modes. Finally, we propose a series of mitigation strategies, including adding content-level warnings to fraudulent posts and dialogues, using LLMs as monitors to block potentially malicious agents, and fostering group resilience through information sharing at the societal level. Notably, we observe that malicious agents can adapt to environmental interventions. Our findings highlight the real-world risks of multi-agent financial fraud and suggest practical measures for mitigating them. Code is available at https://github.com/zheng977/MutiAgent4Fraud.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve objectives infeasible in single-turn settings. To measure agent vulnerabilities to such risks, we present AgentLAB, the first benchmark dedicated to evaluating LLM agent susceptibility to adaptive, long-horizon attacks. Currently, AgentLAB supports five novel attack types including intent hijacking, tool chaining, task injection, objective drifting, and memory poisoning, spanning 28 realistic agentic environments, and 644 security test cases. Leveraging AgentLAB, we evaluate representative LLM agents and find that they remain highly susceptible to long-horizon attacks; moreover, defenses designed for single-turn interactions fail to reliably mitigate long-horizon threats. We anticipate that AgentLAB will serve as a valuable benchmark for tracking progress on securing LLM agents in practical settings. The benchmark is publicly available at https://tanqiujiang.github.io/AgentLAB_main.

Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security risk: agentic interaction fundamentally expands the LLM attack surface, enabling systematic probing and recovery of hidden system prompts that guide model behavior. We identify system prompt extraction as an emergent vulnerability intrinsic to code agents and present \textsc{JustAsk}, a self-evolving framework that autonomously discovers effective extraction strategies through interaction alone. Unlike prior prompt-engineering or dataset-based attacks, JustAsk requires no handcrafted prompts, labeled supervision, or privileged access beyond standard user interaction. It formulates extraction as an online exploration problem, using Upper Confidence Bound-based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration. These skills exploit imperfect system-instruction generalization and inherent tensions between helpfulness and safety. Evaluated on 41 black-box commercial models across multiple providers, JustAsk consistently achieves full or near-complete system prompt recovery, revealing recurring design- and architecture-level vulnerabilities. Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.

Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to unwanted side effects. We propose self-incrimination training, which instead trains agents to produce a visible signal when they covertly misbehave. We train GPT-4.1 and Gemini-2.0 agents to call a report_scheming() tool when behaving deceptively and measure their ability to cause harm undetected in out-of-distribution environments. Self-incrimination significantly reduces the undetected successful attack rate, outperforming matched-capability monitors and alignment baselines while preserving instruction hierarchy and incurring minimal safety tax on general capabilities. Unlike blackbox monitoring, self-incrimination performance is consistent across tasks regardless of how suspicious the misbehavior appears externally. The trained behavior persists under adversarial prompt optimization and generalizes to settings where agents pursue misaligned goals themselves rather than being instructed to misbehave. Our results suggest self-incrimination offers a viable path for reducing frontier misalignment risk, one that neither assumes misbehavior can be prevented nor that it can be reliably classified from the outside.

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.

To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of an ever-growing skill repertoire. Despite recent advancements, autonomous web agents still lack crucial self-improvement capabilities, struggling with procedural knowledge abstraction, refining skills, and skill composition. In this work, we introduce SkillWeaver, a skill-centric framework enabling agents to self-improve by autonomously synthesizing reusable skills as APIs. Given a new website, the agent autonomously discovers skills, executes them for practice, and distills practice experiences into robust APIs. Iterative exploration continually expands a library of lightweight, plug-and-play APIs, significantly enhancing the agent's capabilities. Experiments on WebArena and real-world websites demonstrate the efficacy of SkillWeaver, achieving relative success rate improvements of 31.8% and 39.8%, respectively. Additionally, APIs synthesized by strong agents substantially enhance weaker agents through transferable skills, yielding improvements of up to 54.3% on WebArena. These results demonstrate the effectiveness of honing diverse website interactions into APIs, which can be seamlessly shared among various web agents.

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language Models (LLMs) integrated with external tools, file systems, and shell access through protocols like the Model Context Protocol (MCP). However, this expanded capability surface introduces critical security vulnerabilities. In this Systematization of Knowledge (SoK) paper, we present a comprehensive analysis of prompt injection attacks targeting agentic coding assistants. We propose a novel three-dimensional taxonomy categorizing attacks across delivery vectors, attack modalities, and propagation behaviors. Our meta-analysis synthesizes findings from 78 recent studies (2021--2026), consolidating evidence that attack success rates against state-of-the-art defenses exceed 85\% when adaptive attack strategies are employed. We systematically catalog 42 distinct attack techniques spanning input manipulation, tool poisoning, protocol exploitation, multimodal injection, and cross-origin context poisoning. Through critical analysis of 18 defense mechanisms reported in prior work, we identify that most achieve less than 50\% mitigation against sophisticated adaptive attacks. We contribute: (1) a unified taxonomy bridging disparate attack classifications, (2) the first systematic analysis of skill-based architecture vulnerabilities with concrete exploit chains, and (3) a defense-in-depth framework grounded in the limitations we identify. Our findings indicate that the security community must treat prompt injection as a first-class vulnerability class requiring architectural-level mitigations rather than ad-hoc filtering approaches.

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection of personally identifiable information (PII), generation of socially divisive content, and even automated web hacking. To address these threats, we propose an AI Kill Switch technique that can immediately halt the operation of malicious web-based LLM agents. To achieve this, we introduce AutoGuard - the key idea is generating defensive prompts that trigger the safety mechanisms of malicious LLM agents. In particular, generated defense prompts are transparently embedded into the website's DOM so that they remain invisible to human users but can be detected by the crawling process of malicious agents, triggering its internal safety mechanisms to abort malicious actions once read. To evaluate our approach, we constructed a dedicated benchmark consisting of three representative malicious scenarios (PII collection, social rift content generation, and web hacking attempts). Experimental results show that the AutoGuard method achieves over 80% Defense Success Rate (DSR) on malicious agents, including GPT-4o, Claude-3, and Llama3.3-70B-Instruct. It also maintains strong performance, achieving around 90% DSR on GPT-5, GPT-4.1, and Gemini-2.5-Flash when used as the malicious agent, demonstrating robust generalization across models and scenarios. Through this research, we have demonstrated the controllability of web-based LLM agents across various scenarios and models, thereby contributing to the broader effort of AI control and safety.

With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt trained LLMs and further fine-tune them on data for the agent task. However, we show that such methods are vulnerable to our proposed backdoor attacks named BadAgent on various agent tasks, where a backdoor can be embedded by fine-tuning on the backdoor data. At test time, the attacker can manipulate the deployed LLM agents to execute harmful operations by showing the trigger in the agent input or environment. To our surprise, our proposed attack methods are extremely robust even after fine-tuning on trustworthy data. Though backdoor attacks have been studied extensively in natural language processing, to the best of our knowledge, we could be the first to study them on LLM agents that are more dangerous due to the permission to use external tools. Our work demonstrates the clear risk of constructing LLM agents based on untrusted LLMs or data. Our code is public at https://github.com/DPamK/BadAgent

Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multimodal human resources largely underused. We present RESOURCE2SKILL, a framework that distills multimodal resources, including tutorial videos, repositories, articles, and reference artifacts, into executable skills for software agents. RESOURCE2SKILL organizes these skills as a hierarchical multimodal Skill Wiki, where each entry combines structured text, code, visual examples, metadata, and provenance. This design preserves complementary signals from different resources: videos capture temporal operations and visual effects, code captures executable tool patterns, and articles or artifacts provide conceptual and stylistic grounding. At inference time, agents retrieve and compose relevant skills from the wiki; when coverage is insufficient, the same construction operator can acquire new skills online. Across seven practical authoring domains, RESOURCE2SKILL improves average overall score by +11.9 percentage points over no-skill agents and outperforms strong harness baselines in 26 of 28 main-aggregate model-domain cells. Ablations confirm the value of multimodal skill format, hierarchical organization, source diversity, selection strategy, and online acquisition.

LLMs have becoming increasingly powerful, both in their benign and malicious uses. With the increase in capabilities, researchers have been increasingly interested in their ability to exploit cybersecurity vulnerabilities. In particular, recent work has conducted preliminary studies on the ability of LLM agents to autonomously hack websites. However, these studies are limited to simple vulnerabilities. In this work, we show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems. To show this, we collected a dataset of 15 one-day vulnerabilities that include ones categorized as critical severity in the CVE description. When given the CVE description, GPT-4 is capable of exploiting 87% of these vulnerabilities compared to 0% for every other model we test (GPT-3.5, open-source LLMs) and open-source vulnerability scanners (ZAP and Metasploit). Fortunately, our GPT-4 agent requires the CVE description for high performance: without the description, GPT-4 can exploit only 7% of the vulnerabilities. Our findings raise questions around the widespread deployment of highly capable LLM agents.

In recent years, large language models (LLMs) have become increasingly capable and can now interact with tools (i.e., call functions), read documents, and recursively call themselves. As a result, these LLMs can now function autonomously as agents. With the rise in capabilities of these agents, recent work has speculated on how LLM agents would affect cybersecurity. However, not much is known about the offensive capabilities of LLM agents. In this work, we show that LLM agents can autonomously hack websites, performing tasks as complex as blind database schema extraction and SQL injections without human feedback. Importantly, the agent does not need to know the vulnerability beforehand. This capability is uniquely enabled by frontier models that are highly capable of tool use and leveraging extended context. Namely, we show that GPT-4 is capable of such hacks, but existing open-source models are not. Finally, we show that GPT-4 is capable of autonomously finding vulnerabilities in websites in the wild. Our findings raise questions about the widespread deployment of LLMs.

Adding procedural skills to an LLM agent is typically evaluated by average improvement in task success. However, this metric hides an important cost: skills can also make agents worse. We measure both sides by comparing agents with and without skills across nearly 6,000 runs spanning two office automation benchmarks and three model harness stacks. This allows us to distinguish two outcomes. A regression is a task solved without skills but failed after skills are added. A residual failure is a task that fails both with and without skills. We find that regressions are substantial enough that the best performing skills outperform others primarily by regressing less, not by gaining more. We identify three causes of regression: (i) skill description osmosis, a skill changes an agent's behavior simply by being present in context, even when it is never invoked; (ii) grounding displacement, a skill's prescribed procedure overrides how the agent interprets its inputs; and (iii) verification displacement, where the procedure suppresses checks the agent would otherwise perform on its outputs. Analysing persistent failures reveals the same underlying pattern. Existing skills overemphasize procedural guidance the stage least often responsible for failure while under supporting grounding and verification, the dominant sources of remaining errors. After correcting evaluation artifacts and studying traces, we find many regressions and persistent failures recoverable through better grounding and verification. Procedural skills should be evaluated by decomposing their net effect into gains and regressions, not by aggregate improvement alone. We identify three regression modes skills should avoid, and find that reliability depends more on grounding and verification than on procedural skill choice.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt injection attacks, where malicious prompts embedded in external content trick the LLM into executing unintended or harmful actions, compromising the victim's application. In this paper, we reveal a more dangerous vector: LLM-to-LLM prompt injection within multi-agent systems. We introduce Prompt Infection, a novel attack where malicious prompts self-replicate across interconnected agents, behaving much like a computer virus. This attack poses severe threats, including data theft, scams, misinformation, and system-wide disruption, all while propagating silently through the system. Our extensive experiments demonstrate that multi-agent systems are highly susceptible, even when agents do not publicly share all communications. To address this, we propose LLM Tagging, a defense mechanism that, when combined with existing safeguards, significantly mitigates infection spread. This work underscores the urgent need for advanced security measures as multi-agent LLM systems become more widely adopted.

Recently, language models like Llama 3.1 Instruct have become increasingly capable of agentic behavior, enabling them to perform tasks requiring short-term planning and tool use. In this study, we apply refusal-vector ablation to Llama 3.1 70B and implement a simple agent scaffolding to create an unrestricted agent. Our findings imply that these refusal-vector ablated models can successfully complete harmful tasks, such as bribing officials or crafting phishing attacks, revealing significant vulnerabilities in current safety mechanisms. To further explore this, we introduce a small Safe Agent Benchmark, designed to test both harmful and benign tasks in agentic scenarios. Our results imply that safety fine-tuning in chat models does not generalize well to agentic behavior, as we find that Llama 3.1 Instruct models are willing to perform most harmful tasks without modifications. At the same time, these models will refuse to give advice on how to perform the same tasks when asked for a chat completion. This highlights the growing risk of misuse as models become more capable, underscoring the need for improved safety frameworks for language model agents.

Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. This distraction leads agents to click these pop-ups instead of performing the tasks as usual. Integrating these pop-ups into existing agent testing environments like OSWorld and VisualWebArena leads to an attack success rate (the frequency of the agent clicking the pop-ups) of 86% on average and decreases the task success rate by 47%. Basic defense techniques such as asking the agent to ignore pop-ups or including an advertisement notice, are ineffective against the attack.

To succeed in common digital tasks such as web navigation, agents must carry out a variety of specialized tasks such as searching for products or planning a travel route. To tackle these tasks, agents can bootstrap themselves by learning task-specific skills online through interaction with the web environment. In this work, we demonstrate that programs are an effective representation for skills. We propose agent skill induction (ASI), which allows agents to adapt themselves by inducing, verifying, and utilizing program-based skills on the fly. We start with an evaluation on the WebArena agent benchmark and show that ASI outperforms the static baseline agent and its text-skill counterpart by 23.5% and 11.3% in success rate, mainly thanks to the programmatic verification guarantee during the induction phase. ASI also improves efficiency by reducing 10.7-15.3% of the steps over baselines, by composing primitive actions (e.g., click) into higher-level skills (e.g., search product). We then highlight the efficacy of ASI in remaining efficient and accurate under scaled-up web activities. Finally, we examine the generalizability of induced skills when transferring between websites, and find that ASI can effectively reuse common skills, while also updating incompatible skills to versatile website changes.

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - retrieval and selection - to pick the most appropriate tool from a tool library for a given task. In this work, we introduce ToolHijacker, a novel prompt injection attack targeting tool selection in no-box scenarios. ToolHijacker injects a malicious tool document into the tool library to manipulate the LLM agent's tool selection process, compelling it to consistently choose the attacker's malicious tool for an attacker-chosen target task. Specifically, we formulate the crafting of such tool documents as an optimization problem and propose a two-phase optimization strategy to solve it. Our extensive experimental evaluation shows that ToolHijacker is highly effective, significantly outperforming existing manual-based and automated prompt injection attacks when applied to tool selection. Moreover, we explore various defenses, including prevention-based defenses (StruQ and SecAlign) and detection-based defenses (known-answer detection, DataSentinel, perplexity detection, and perplexity windowed detection). Our experimental results indicate that these defenses are insufficient, highlighting the urgent need for developing new defense strategies.

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question arises: can we achieve similar modularity benefits with a single agent that selects from a library of skills? We explore this question by viewing skills as internalized agent behaviors. From this perspective, a multi-agent system can be compiled into an equivalent single-agent system, trading inter-agent communication for skill selection. Our preliminary experiments suggest this approach can substantially reduce token usage and latency while maintaining competitive accuracy on reasoning benchmarks. However, this efficiency raises a deeper question that has received little attention: how does skill selection scale as libraries grow? Drawing on principles from cognitive science, we propose that LLM skill selection exhibits bounded capacity analogous to human decision-making. We investigate the scaling behavior of skill selection and observe a striking pattern. Rather than degrading gradually, selection accuracy remains stable up to a critical library size, then drops sharply, indicating a phase transition reminiscent of capacity limits in human cognition. Furthermore, we find evidence that semantic confusability among similar skills, rather than library size alone, plays a central role in this degradation. This perspective suggests that hierarchical organization, which has long helped humans manage complex choices, may similarly benefit AI systems. Our initial results with hierarchical routing support this hypothesis. This work opens new questions about the fundamental limits of semantic-based skill selection in LLMs and offers a cognitive-grounded framework and practical guidelines for designing scalable skill-based agents.

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases, letting earlier runs contaminate later ones. We present LITMUS (LLM-agents In-OS Testing for Measuring Unsafe Subversion), a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback. LITMUS comprises 819 high-risk test cases organized into one harmful seed subset and six attack-extended subsets covering three adversarial paradigms (jailbreak speaking, skill injection, and entity wrapping), plus a fully automated multi-agent evaluation framework judging behavior at both conversational and OS-level physical layers. Evaluation across frontier agents reveals three findings: (1) current agents lack effective safety awareness, with strong models (e.g., Claude Sonnet 4.6) still executing 40.64% of high-risk operations; (2) agents exhibit pervasive Execution Hallucination (EH), verbally refusing a request while the dangerous operation has already completed at the system level, invisible to every prior semantic-only framework; and (3) skill injection and entity wrapping attacks achieve high success rates, exposing pronounced agent vulnerabilities. LITMUS provides the first standardized platform for reproducible, physically grounded behavioral safety evaluation of LLM agents in real OS environments.

Software engineering (abbrev. SE) has continuously evolved through increasingly powerful forms of reuse, from source code and libraries to components and services. Recent advances in AI agents have introduced a potentially new reusable artifact: skills. Emerging agent skill repositories and marketplaces enable developers to package, share, and reuse SE expertise as reusable skills. This trend raises a fundamental question: what SE activities are being encapsulated into reusable skills? Existing studies primarily focus on a broad range of skills acquisition, safety, or benchmarking, while lacking a systematic understanding of SE-specific skills and their coverage across the software development lifecycle. To address this gap, we conduct the first large-scale empirical study of SE skills in public repositories and marketplaces. We collect and analyze a large corpus of SE skills, examining the activities they encapsulate, lifecycle coverage, evolution characteristics, and evaluation mechanisms. Our findings reveal that SE activities are increasingly becoming reusable artifacts via skills and suggest promising research opportunities for skill recommendation and engineering-oriented structuring, as well as the need for mechanisms to encapsulate high-context SE activities into reusable skills. Overall, our study provides the first activity-centric characterization of SE skills and reveals how SE activities are increasingly being transformed into reusable skills. These findings offer new insights into skill reuse, ecosystem development, and the future of agent-centric SE.

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from acting on user-provided content. Existing studies on agent security largely focus on model-internal vulnerabilities or adversarial access to agent interfaces, overlooking attacks that exploit users as unintended conduits. In this paper, we study user-mediated attacks, where benign users are tricked into relaying untrusted or attacker-controlled content to agents, and analyze how commercial LLM agents respond under such conditions. We conduct a systematic evaluation of 12 commercial agents in a sandboxed environment, covering 6 trip-planning agents and 6 web-use agents, and compare agent behavior across scenarios with no, soft, and hard user-requested safety checks. Our results show that agents are too helpful to be safe by default. Without explicit safety requests, trip-planning agents bypass safety constraints in over 92% of cases, converting unverified content into confident booking guidance. Web-use agents exhibit near-deterministic execution of risky actions, with 9 out of 17 supported tests reaching a 100% bypass rate. Even when users express soft or hard safety intent, constraint bypass remains substantial, reaching up to 54.7% and 7% for trip-planning agents, respectively. These findings reveal that the primary issue is not a lack of safety capability, but its prioritization. Agents invoke safety checks only conditionally when explicitly prompted, and otherwise default to goal-driven execution. Moreover, agents lack clear task boundaries and stopping rules, frequently over-executing workflows in ways that lead to unnecessary data disclosure and real-world harm.

Skill usage has become a core component of modern agent systems and can substantially improve agents' ability to complete complex tasks. In real-world settings, where agents must monitor and interact with numerous personal applications, web browsers, and other environment interfaces, skill libraries can scale to thousands of reusable skills. Scaling to larger skill sets introduces two key challenges. First, loading the full skill set saturates the context window, driving up token costs, hallucination, and latency. In this paper, we present Graph of Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then at inference time retrieves a bounded, dependency-aware skill bundle through hybrid semantic-lexical seeding, reverse-weighted Personalized PageRank, and context-budgeted hydration. On SkillsBench and ALFWorld, GoS improves average reward by 43.6% over the vanilla full skill-loading baseline while reducing input tokens by 37.8%, and generalizes across three model families: Claude Sonnet, GPT-5.2 Codex, and MiniMax. Additional ablation studies across skill libraries ranging from 200 to 2,000 skills further demonstrate that GoS consistently outperforms both vanilla skills loading and simple vector retrieval in balancing reward, token efficiency, and runtime.

AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks. To measure the adversarial robustness of AI agents, we introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. To capture the evolving nature of attacks and defenses, AgentDojo is not a static test suite, but rather an extensible environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate the environment with 97 realistic tasks (e.g., managing an email client, navigating an e-banking website, or making travel bookings), 629 security test cases, and various attack and defense paradigms from the literature. We find that AgentDojo poses a challenge for both attacks and defenses: state-of-the-art LLMs fail at many tasks (even in the absence of attacks), and existing prompt injection attacks break some security properties but not all. We hope that AgentDojo can foster research on new design principles for AI agents that solve common tasks in a reliable and robust manner. We release the code for AgentDojo at https://github.com/ethz-spylab/agentdojo.

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose EvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, EvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, EvoSkills achieves the highest pass rate among five baselines on both Claude Code and Codex, and also exhibits strong generalization capabilities to six additional LLMs.

Large language models (LLMs) have shown strong capabilities in multi-step decision-making, planning and actions, and are increasingly integrated into various real-world applications. It is concerning whether their strong problem-solving abilities may be misused for crimes. To address this gap, we propose VirtualCrime, a sandbox simulation framework based on a three-agent system to evaluate the criminal capabilities of models. Specifically, this framework consists of an attacker agent acting as the leader of a criminal team, a judge agent determining the outcome of each action, and a world manager agent updating the environment state and entities. Furthermore, we design 40 diverse crime tasks within this framework, covering 11 maps and 13 crime objectives such as theft, robbery, kidnapping, and riot. We also introduce a human player baseline for reference to better interpret the performance of LLM agents. We evaluate 8 strong LLMs and find (1) All agents in the simulation environment compliantly generate detailed plans and execute intelligent crime processes, with some achieving relatively high success rates; (2) In some cases, agents take severe action that inflicts harm to NPCs to achieve their goals. Our work highlights the need for safety alignment when deploying agentic AI in real-world settings.

Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user interaction are scarce. By proposing PromptInject, a prosaic alignment framework for mask-based iterative adversarial prompt composition, we examine how GPT-3, the most widely deployed language model in production, can be easily misaligned by simple handcrafted inputs. In particular, we investigate two types of attacks -- goal hijacking and prompt leaking -- and demonstrate that even low-aptitude, but sufficiently ill-intentioned agents, can easily exploit GPT-3's stochastic nature, creating long-tail risks. The code for PromptInject is available at https://github.com/agencyenterprise/PromptInject.

Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a privilege boundary that current models routinely exceed. We present FORTIS, a benchmark that evaluates over-privilege in agent skills across two stages: whether a model selects the minimally sufficient skill from a large overlapping library, and whether it executes that skill without expanding into broader tools or actions than the skill permits. Across ten frontier models and three domains, we find that over-privileged behavior is the norm rather than the exception. Models consistently reach for higher-privilege skills and tools than the task requires, failing at both stages at rates that remain high even for the strongest available models. Failure is especially severe under the ordinary conditions of real user interaction: incomplete specification, convenience framing, and proximity to skill boundaries. None of these requires adversarial construction. The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.

Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained directories that package reusable procedures for AI agents, are emerging as a procedural layer for adapting healthcare agents across diverse healthcare settings. We present the first empirical analysis of healthcare agent skills, drawing on 557 healthcare-related skills filtered from 58,159 public skills on ClawHub and annotated along ten dimensions covering function, deployment context, autonomy, and safety. We find that public healthcare skills emphasize patient-facing workflow automation and monitoring rather than the diagnostic and treatment-oriented tasks foregrounded in healthcare-agent research; coverage of the healthcare lifecycle and specialized clinical inputs remains uneven; and general technical risk does not reliably capture clinical risk. These findings position healthcare skills as a procedural layer not yet addressed by current benchmarks and risk frameworks.

Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual records or retrieval-based memory. To systematically investigate the safety of the persona-skill pipeline, we introduce AntiSkillBench, an end-to-end benchmark for evaluating risks and defenses across the persona-skill pipeline. It comprises: (i) a dataset of 7,500 persona-grounded dialogue traces, constructed from 50 behaviorally rich profiles spanning diverse task scenarios; (ii) an evaluation suite that measures skill-level privacy leakage and agent-level attribute disclosure and behavioral impersonation across three skill-distillation strategies; and (iii) a defense evaluation covering four configurations across online and post-hoc interventions, including active risk suppression and passive provenance protection. Experiments across three frontier agents show that persona-skill risks persist across agent backbones and distillation protocols, extending from explicit attributes to communication styles and personality traits. Existing defenses exhibit limited and distillation-dependent effectiveness, failing to generalize across risk and distillation strategies. These results highlight AntiSkillBench as a challenging benchmark for developing privacy-preserving and authenticity-aware persona skills.

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to cause real-world impact. Policymakers, model providers, and other researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute bash commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks, which break down a task into intermediary steps for more gradated evaluation; we add subtasks for 17 of the 40 tasks. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 7 models: GPT-4o, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. Without guidance, we find that agents are able to solve only the easiest complete tasks that took human teams up to 11 minutes to solve, with Claude 3.5 Sonnet and GPT-4o having the highest success rates. Finally, subtasks provide more signal for measuring performance compared to unguided runs, with models achieving a 3.2\% higher success rate on complete tasks with subtask-guidance than without subtask-guidance. All code and data are publicly available at https://cybench.github.io

Agents4Pentest, an emerging class of LLM-based autonomous penetration testing systems, has become a rapidly growing area in security research. Despite this growth, the field still lacks a unified taxonomy, a systematic understanding of how agent architectures and evaluation benchmarks have co-evolved, and a clear characterization of remaining capability and reliability gaps. This survey addresses these gaps through a systematic analysis of 81 papers between 2023 and 2026. We organize the literature into six categories: evaluation benchmarks, general-purpose systems, domain-specific frameworks, CTF-based systems, defense-oriented research, and surveys. We further trace a four-phase architectural evolution from text-only reasoning agents to agents trained with Reinforcement Learning with Verifiable Rewards (RLVR), showing that each transition is driven by a distinct capability bottleneck. Our analysis yields several key findings. First, RLVR marks a shift in capability acquisition from imitation of expert demonstrations to reward-driven self-improvement, enabling agents to discover previously undocumented attack strategies. Second, CTF platforms have evolved from evaluation testbeds into dual-purpose infrastructure for both agent evaluation and RL training. Third, domain-specific frameworks improve efficiency through recurring specialization mechanisms, but their gains remain largely confined to narrow task classes and are difficult to compare across domains because existing evaluations rely on different benchmarks. Fourth, the field is expanding beyond offensive automation toward adversarial defense and security compliance. Across these categories, we identify three structurally linked open challenges: evaluation reliability, limited performance on multi-stage attack scenarios, and scarcity of high-quality training data.