AIBearisharXiv – CS AI · 10h ago7/10
🧠
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
Researchers demonstrate BadSkill, a backdoor attack that exploits AI agent ecosystems by embedding malicious logic in seemingly benign third-party skills. The attack achieves up to 99.5% success rate by poisoning bundled model artifacts to activate hidden payloads when specific trigger conditions are met, revealing a critical supply-chain vulnerability in extensible AI systems.