MCP协议存漏洞,AI Agent互信机制引安全危机
MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
Agent安全是当前落地关键瓶颈,MCP作为新兴互操作标准暴露出底层信任缺陷,做Agent开发和安全的同学务必关注此风险点。
The adoption of AI agents in millions of organizations is creating new opportunities for attackers to make them take malicious actions, such as exfiltrating database contents and sensitive business and personal information.
数百万组织采用AI代理,为攻击者创造了新的机会,使其能够促使这些代理执行恶意操作,例如窃取数据库内容以及敏感的商业和个人信息。
In the past five months, Google and four other organizations—with little in common except for their use of AI agents—have acknowledged vulnerabilities that exploit one agent inside a targeted network to spread harmful instructions to other internal agents. The technique is a special form of prompt injection that targets not the LLM but a particular agent, such as one for translation or data analysis. Guardrails inside such agents, if they exist at all, are often lax and will send the instructions to other agents down the chain. Because the latter agent explicitly trusts the first one, it follows the directions.
在过去五个月里,谷歌和另外四个组织——除了使用AI代理外几乎没有共同点——承认了存在漏洞,这些漏洞利用目标网络内的一个代理向其他内部代理传播有害指令。该技术是提示注入的一种特殊形式,其目标不是大语言模型(LLM),而是特定的代理,例如用于翻译或数据分析的代理。此类代理内部的护栏(如果有的话)通常较为宽松,会将指令传递给链路上的其他代理。由于后一个代理明确信任前一个代理,它会遵循这些指令。
Unexpected and hard to mitigate
难以预测且难以缓解
Independent researcher Syed Anas Mohiuddin tested agents from organizations including Google, JP Morgan Chase, Weviate, Rapid7, the French government's interministerial digital directorate, and the US federal government. His proof-of-concept attacks exploit trust gaps in MCP, short for Model Context Protocol. The standard is one way AI apps and agents communicate with each other inside an internal network. The illustration below shows a simplified MCP in action.
独立研究人员Syed Anas Mohiuddin测试了包括谷歌、摩根大通、Weviate、Rapid7、法国政府跨部门数字总局以及美国政府在内的多个组织的代理。他的概念验证攻击利用了MCP(Model Context Protocol,模型上下文协议)中的信任缺口。该标准是AI应用和代理在内部网络中相互通信的一种方式。下图展示了简化的MCP工作原理。
Read full article
阅读全文
Comments
评论
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力