# SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs

arXiv: https://arxiv.org/abs/2609.36879 · HTML: https://mlsanity.com/paper/2609.36879/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 29 Sep 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, 24 of 24)

- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026)
- ["Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild](https://mlsanity.com/paper/2602.06547/) (2026)
- [Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends](https://mlsanity.com/paper/2409.14457/) (2024)
- [SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems](https://mlsanity.com/paper/2604.06811/) (2026)
- [SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills](https://mlsanity.com/paper/2604.06550/) (2026)
- [MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills](https://mlsanity.com/paper/2606.07131/) (2026)
- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [CODESKILL: Learning Self-Evolving Skills for Coding Agents](https://mlsanity.com/paper/2605.25430/) (2026)
- [HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?](https://mlsanity.com/paper/2604.15415/) (2026)
- [Detecting Malicious Agent Skills in the Wild using Attention](https://mlsanity.com/paper/2606.23416/) (2026)
- [Dynamic Malicious Skills in Agentic AI](https://mlsanity.com/paper/2606.16287/) (2026)
- [AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery](https://mlsanity.com/paper/2504.07421/) (2025)
- [Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions](https://mlsanity.com/paper/2412.06113/) (2024)
- [SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills](https://mlsanity.com/paper/2606.15899/) (2026)
- [Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills](https://mlsanity.com/paper/2605.12875/) (2026)

## Abstract (arXiv)

As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent Skill packages task-specific instructions with executable components and auxiliary resources to provide specialized functionalities. However, the growing adoption of third-party Skills introduces a new supply-chain attack surface. Malicious Skills can embed harmful behaviors that abuse agent privileges and compromise the agent execution environment or accessible resources. Although recent LLM-based malicious Skill auditing approaches have achieved promising performance, they often rely on capable commercial LLMs. How to achieve effective auditing with compact, locally deployable LLMs in security-sensitive and resource-constrained settings remains largely unexplored. Our investigation reveals that compact LLMs struggle to identify malicious behaviors hidden in complex Skill packages. This difficulty arises from both the implicit nature of such behaviors and the limited reasoning capacity of compact LLMs. To address these challenges, we propose SKILLLITE, an evidence-guided agentic framework for malicious Skill detection. SKILLLITE effectively extracts security-relevant behaviors and infers the intended functionality from complex Skill packages. It then employs a compact LLM to assess the maliciousness of the Skill based on the observed behaviors and their functional context. Experiments show that SKILLLITE improves malicious Skill detection across different compact LLM backbones and outperforms existing representative auditing baselines. Its effectiveness generalizes to behaviorally confirmed in-the-wild malicious Skills. Meanwhile, SKILLLITE maintains a low inference latency, supporting its practical deployment.