HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?

Abstract

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills

Categories

Framework mappings

Suggested from the entry's categories.

@misc{jiang2026harmfulskillbench,
  title = {{HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?}},
  author = {Yukun Jiang and Yage Zhang and Michael Backes and Xinyue Shen and Yang Zhang},
  year = {2026},
  month = apr,
  eprint = {2604.15415},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.15415}
}