SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs

arXiv:2609.36879 · cs.CR, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/cisco-ai-defense/skill-scanner

Terminology

• Agent Skills — 25× in this paper · explained in 1 episode
• Benchmark — 23× in this paper · explained in 2 episodes
• Analyzer — 11× in this paper · explained in 1 episode
• Grounding — 7× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Contextual Understanding — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Reverse Shell — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic Architecture — 1× in this paper · explained in 1 episode
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cooperation — 1× in this paper · explained in 2 episodes
• False Negative Rate — 1× in this paper
• False Positive Rate — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Intent Mismatch — 1× in this paper
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Shadow Feature — 1× in this paper
• Structured Reasoning — 1× in this paper · explained in 3 episodes

Sources

• AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• Dynamic Malicious Skills in Agentic AI
• Detecting Malicious Agent Skills in the Wild using Attention
• SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
• MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
• SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
• Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills
• Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem
• SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
• HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
• Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
• CODESKILL: Learning Self-Evolving Skills for Coding Agents
• SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
• "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
• MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
• "Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts
• Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs