新协议存在信任漏洞,可让恶意提示从一个Agent传播至另一个Agent。
原文:https://arstechnica.com/security/2026/10/vulnerability-in-agents-from-google-and-others-exposes-structural-flaw-in-mcp/
MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
Agent新协议存在信任漏洞,可让恶意提示从一个Agent传播至另一个Agent。
原文:https://arstechnica.com/security/2026/10/vulnerability-in-agents-from-google-and-others-exposes-structural-flaw-in-mcp/
评论区 0 条讨论