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

Key points

• 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.1
• 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.1
• His proof-of-concept attacks exploit trust gaps in MCP, short for Model Context Protocol.1
• The standard is one way AI apps and agents communicate with each other inside an internal network.1

Sources (1)

• [1]MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
  Ars Technica: AI · Oct 5, 10:26 PM

  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.

Extractive summary: sentences quoted from the sources.