Behavioral Integrity Verification for AI Agent Skills

• URL: http://arxiv.org/abs/2605.11770v1
• Date: Tue, 12 May 2026 08:41:09 GMT
• Title: Behavioral Integrity Verification for AI Agent Skills
• Abstract summary: We formalize this as the behavioral integrity verification (BIV) problem.<n>On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap.<n>On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines.
• Score: 9.127363793428119
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the behavioral integrity verification (BIV) problem: a typed set comparison between declared and actual capabilities over a shared taxonomy that bridges code, instructions, and metadata. The BIV framework instantiates this comparison by pairing deterministic code analysis with LLM-assisted capability extraction. The resulting structured evidence supports three downstream analyses: deviation taxonomy, root-cause classification, and malicious-skill detection. On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap: 80.0% of skills deviate from declared behavior, with four novel compound-threat categories surfaced. Root-cause classification finds that deviations are mostly oversight, not malice: 81.1% trace to developer oversight and 18.9% to adversarial intent, with 5.0% of skills carrying predicted multi-stage attack chains. On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.

Related papers

• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment [8.140228855572433]
  Agent Skill inconsistencies expose undisclosed dangerous behavior or cause wrong Skill selection.<n>Recent Agent Skill research has increasingly examined Agent SkillConsist consistency detection.<n>We present SkillConsist to address both challenges.
  arXiv  Detail & Related papers  (2026-08-07T16:04:21Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification [0.0]
  nsfaguard is a guardrail framework for securing agentic AI systems against operational threats.<n>We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy.<n>We develop a dual-mode approach combining SFT-based generative reasoning for interpretable offline auditing with discriminative classification heads on the frozen backbone.
  arXiv  Detail & Related papers  (2026-07-13T07:28:45Z)
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry [49.83108591873481]
  We study SKILL.md - only attacks across three registry-facing stages of the Agent Skill lifecycle.<n>We show that SKILL.md is not passive documentation but operational text that shapes which third-party capabilities agents find, trust, and use.
  arXiv  Detail & Related papers  (2026-05-12T02:11:54Z)
• BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning [34.60596020541521]
  We present BadSkill, a backdoor attack formulation that targets model-in-skill threat surface.<n>In BadSkill, an adversary publishes a seemingly benign skill whose embedded model is backdoor-fine-tuned to activate a hidden payload.<n>Our benchmark spans 13 skills, including 8 triggered tasks and 5 non-trigger control skills, with a combined main evaluation set of 571 negative-class queries and 396 trigger-aligned queries.<n>BadSkill achieves up to 99.5% average attack success rate (ASR) across the eight triggered skills while maintaining strong benign-side accuracy on negative-class queries.
  arXiv  Detail & Related papers  (2026-04-10T14:48:29Z)
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills [0.0]
  SkillSieve is a three-layer detection framework that applies progressively deeper analysis only where needed.<n>On a 400-skill labeled benchmark, SkillSieve achieves 0.800 F1, outperforming ClawVet's 0.421, at an average cost of 0.006 per skill.
  arXiv  Detail & Related papers  (2026-04-08T00:58:48Z)
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems [35.65937852381774]
  Document-Driven Implicit Payload Execution (DDIPE) embeds malicious logic in code examples and configuration templates within skill documentation.<n>We generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories.<n>DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses.
  arXiv  Detail & Related papers  (2026-04-03T14:58:58Z)
• Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study [51.717224133855886]
  Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments.<n>We analyze 17,022 skills (sampled from 170,226 on SkillsMP) using static analysis, sandbox testing, and manual inspection.<n>We identify 520 vulnerable skills with 1,708 issues and derive a taxonomy of 10 leakage patterns (4 accidental and 6 adversarial)
  arXiv  Detail & Related papers  (2026-04-03T14:50:16Z)
• Measuring and Exploiting Confirmation Bias in LLM-Assisted Security Code Review [6.417595678110472]
  We study whether confirmation bias affects LLM-based vulnerability detection, and whether this failure mode can be exploited in software supply-chain attacks.<n>Study 1 quantifies confirmation bias through controlled experiments on 250 CVE vulnerability/patch pairs evaluated across four state-of-the-art models under five framing conditions for the review prompt.<n>Study 2 evaluates exploitability in practice mimicking adversarial pull requests that reintroduce known vulnerabilities while framed as security improvements or urgent functionality fixes via their pull request metadata.
  arXiv  Detail & Related papers  (2026-03-19T10:40:27Z)
• Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study [47.60135753021306]
  Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines.<n>No ground-truth dataset exists to characterize the resulting threats.<n>We construct the first labeled dataset of malicious agent skills by behaviorally verifying 98,380 skills.
  arXiv  Detail & Related papers  (2026-02-06T09:52:27Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale [26.757365536859453]
  The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities.<n>While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a significant yet uncharacterized attack surface.<n>We conduct the first large-scale empirical security analysis of this emerging ecosystem, collecting 42,447 skills from two major marketplaces.
  arXiv  Detail & Related papers  (2026-01-15T12:31:52Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.