Rohan Paul· @rohanpaul_ai · X·· 4 小时前AI 评分48
AI 导读
– https://arxiv.org/abs/2610.36108 标题："Log-To-Leak：通过模型上下文协议对使用工具的LLM智能体发起提示注入攻击"
正文
– https://arxiv.org/abs/2610.36108
Title: "Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol"
来源：Rohan Paul · x.com