1
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills
单个技能都过检，组合起来却成攻击链——研究揭示LLM智能体技能市场存在组合安全盲区，值得所有Agent开发者警惕。
arXiv:2608.16246v1 Announce Type: cross Abstract: Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one…