Seungho Son

Content-Hiding Attacks and Defenses for LLM-Based Agent-Skill Scanners

AI agent “skills” (a natural-language SKILL.md plus bundled scripts) are distributed through marketplaces and public Git repositories, and a growing set of scanners classify them as safe or malicious, increasingly with a large language model (LLM) as the judge. We ask where these LLM-based scanners actually fail. Using...