← 研踪 PaperTrailarXiv:2605.11770 · v2
Behavioral Integrity Verification for AI Agent Skills
首次提交 2026-05-12 16:41
版本更新 2026-11-19 04:16
雷达观测 2026-11-21 12:18
摘要
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 have at least one deviation in the taxonomy, with four 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 0.949, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.
作者备注:Accepted at the NeurIPS 2026 Workshop on Who Verifies the Agents? Toward Reliable Agent Development
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 04:16 · 最新观测版本
Behavioral Integrity Verification for AI Agent Skills
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 have at least one deviation in the taxonomy, with four 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 0.949, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.
查看此版本解读 →查看此版本原文 ↗