Skip to content
Industry only#MCP/Tool Calling
Oct 7Wed
Oct 5Mon
  1. Ars Technica · AI38

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

    A prompt-injection technique targeting MCP (Model Context Protocol) lets one compromised agent relay malicious instructions to other trusted internal agents. Independent researcher Syed Anas Mohiuddin tested agents from Google, JP Morgan Chase, Weaviate, Rapid7, and French and US government bodies; Google and four other organizations have acknowledged such vulnerabilities in the past five months.