SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems 事件

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems arXiv:2604.06811v2 Announce Type: replace-cross Abstract: Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverag