ai

MCP for agent-to-agent comms may be the riskiest protocol you've never heard of

原作者:Dan Goodin

来源原始要点

Trust gaps in the new protocol spread malicious prompts from one agent to another.

查看完整报道

完整图文、背景资料与讨论归原始发布平台 Ars Technica 所有。

直达原文报道 ↗