Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills

arXiv:2610.19264 · cs.CR, cs.AI · Submitted 2026-10-13 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: This paper has 13 pages, 9 figures, and 3 tables

Code: https://github.com/agentskills/agentskills

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Agent Skills — 1× in this paper

Sources

• Scanning the Harness: Configuration Exposures in AI Coding-Agent Supply Chains
• SkillGuard: A Permission-Centric Framework for Agent Skill Security
• Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
• "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
• From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained
• CONTRA: Red-Teaming Configurations of Personalizable Agents
• How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

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
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills