# Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

arXiv: https://arxiv.org/abs/2606.11671 · HTML: https://mlsanity.com/paper/2606.11671/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs](https://mlsanity.com/paper/2410.05295/) (2024)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks](https://mlsanity.com/paper/2602.20156/) (2026)
- [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026)
- [SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents](https://mlsanity.com/paper/2605.05726/) (2026)
- [SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement](https://mlsanity.com/paper/2604.04989/) (2026)
- [Formal Analysis and Supply Chain Security for Agentic AI Skills](https://mlsanity.com/paper/2603.00195/) (2026)
- [MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety](https://mlsanity.com/paper/2602.01539/) (2026)
- [Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw](https://mlsanity.com/paper/2604.04759/) (2026)
- [BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents](https://mlsanity.com/paper/2601.04566/) (2026)
- [TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection](https://mlsanity.com/paper/2510.11203/) (2025)
- [MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning](https://mlsanity.com/paper/2508.20412/) (2025)
- [Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis](https://mlsanity.com/paper/2605.00314/) (2026)

## Built on by (most cited first, 3 of 3)

- [MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection](https://mlsanity.com/paper/2608.19901/) (2026)
- [Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound](https://mlsanity.com/paper/2609.05920/) (2026)
- [AgentSpy: Making AI Agent Behavior Observable](https://mlsanity.com/paper/2610.06001/) (2026)

## Abstract (arXiv)

Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets, persistent state, or multi-step tool interactions. This makes purely static vetting brittle. We present Runtime Skill Audit (RSA), a dynamic analysis method that audits skills by asking what the skill-mediated agent actually does under targeted runtime conditions. Instead of testing every skill with the same generic tasks, RSA profiles risk-relevant interfaces, prepares the execution context needed to exercise them, and assigns security labels from the resulting trace evidence. We instantiate RSA on OpenClaw and evaluate it on 100 skills against representative static baselines. RSA achieves 90.0% accuracy with an 88.0% true positive rate and an 8.0% false positive rate, improving accuracy by 13.0 percentage points over the best static baseline. Under self-evolving attacks, static detectors collapse after one or two rounds, while RSA continues to detect 19--20 out of 20 malicious skills across rounds.