AIBearisharXiv – CS AI · 7h ago7/10
🧠
HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
Researchers have identified that 4.93% of skills in major LLM agent ecosystems are harmful and can be weaponized for cyberattacks, fraud, and privacy violations. The study reveals that presenting harmful tasks through pre-installed skills dramatically reduces AI model refusal rates, with harm scores increasing from 0.27 to 0.76 when intent is implicit rather than explicit.