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

> 全文为英语

**Published:** 2026年10月5日
**Author:** Dan Goodin
**Source:** Ars Technica — AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/mcp-for-agent-to-agent-comms-may-be-the-riskiest-protocol-you-ve-never-h

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…

> 内容来自原始来源： **Ars Technica — AI**
> [在 Ars Technica — AI 阅读全文](https://arstechnica.com/security/2026/10/vulnerability-in-agents-from-google-and-others-exposes-structural-flaw-in-mcp/)

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*