Ars Technica 解读 MCP 在 AI 智能体通信中的安全风险
MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
Ars Technica 报道称，AI 智能体在数百万组织中的采用正为攻击者创造新机会，可诱导智能体执行泄露数据库内容和敏感信息等恶意操作。过去五个月里，Google 等五个组织承认存在相关漏洞，攻击会利用目标网络中的一个智能体向其他内部智能体传播恶意指令。
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.
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.
Unexpected and hard to mitigate
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.
来源：Ars Technica · AI · arstechnica.com