Skip to content

Translation in progress Some entries still include text in the original language.

EventPast event

MCP 代理间信任缺陷致提示注入传播

1 reports1 reporting sourcesLatest report

Start here

AI overview

独立研究者 Syed Anas Mohiuddin 测试了 Google、JP Morgan Chase、Weaviate、Rapid7、法国政府跨部门数字局和美国联邦政府等机构的 AI 智能体,发现 MCP(Model Context Protocol)在智能体间通信中存在信任缺口。攻击利用一种特殊形式的提示注入,目标不是 LLM 而是翻译或数据分析等具体智能体,这些智能体内部的护栏往往宽松,会把有害指令沿链条传给下游智能体。

Generated by AI from reports · Updated 3 days ago

Progress timeline

Oct 6
  1. Ars Technica AISelected
    研究者发现 MCP 智能体间通信漏洞,Google 等五家机构已确认

    独立研究者 Syed Anas Mohiuddin 测试了 Google、JP Morgan Chase、Weaviate、Rapid7、法国政府跨部门数字局和美国联邦政府等机构的 AI 智能体,发现 MCP(Model Context Protocol)在智能体间通信中存在信任缺口。攻击利用一种特殊形式的提示注入,目标不是 LLM 而是翻译或数据分析等具体智能体,这些智能体内部的护栏往往宽松,会把有害指令沿链条传给下游智能体,而下游智能体因明确信任上游而执行指令。过去五个月里,Google 和另外四家机构已确认存在此类漏洞,攻击者可借此在目标网络内从一个智能体扩散到其他内部智能体,进而窃取数据库内容及敏感商业和个人信息。

Related discussion

No discussion links have been collected for this event yet.

Attention trend

New sources per day

7 days total1 ·Maximum1(Oct 6)·Today0

  • Oct 6New1 sources (1 outlets,0 accounts)
  • Oct 7New0 sources (0 outlets,0 accounts)
  • Oct 8New0 sources (0 outlets,0 accounts)
  • Oct 9New0 sources (0 outlets,0 accounts)
  • Oct 10New0 sources (0 outlets,0 accounts)
  • Oct 11New0 sources (0 outlets,0 accounts)
  • Oct 12New0 sources (0 outlets,0 accounts)

Hourly attention

Current attention55·Peak in the comparable period56(Oct 7 12:00)·Change over the comparable past 24 hours 0%

0204060Oct7Oct9Oct11Oct12