1
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
揭秘LLM智能体技能如何无意间泄露你的登录凭证，基于实证研究的新发现。
arXiv:2604.03070v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents increasingly rely on third-party skills that operate withi…