“checkpoints” — 54 distilled results

SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents

21929v1 Announce Type: new Abstract: Agent skills extend coding agents with task-specific instructions, scripts, and resources, but they also create a trusted instruction channel that can be abused beyond conventional security attacks. This paper studies token amplification through skill injection: an economic resource-abuse threat in which a malicious skill causes an agent to consume substantially more tokens than needed for normal task execution.

rss:arxiv-cscr 20d ago · rss:arxiv-cscr 33d ago