AI News/Wire summary
Attackers can pivot between AI agents using MCP trust gaps, researcher finds
Key points
- Independent researcher Syed Anas Mohiuddin tested agents at Google, JP Morgan Chase, Rapid7 and US and French government bodies, among others.
- Attacks use one compromised agent to pass malicious instructions to other agents, which trust the sender and run them.
- Google's flaw was rated 8 out of 10 and involved an MCP database toolbox that could be made to send requests to internal endpoints.
- Rapid7's flaw, CVE-2026-97228, was rated 2.7 out of 10 and was fixed last month.
Why it matters for marketers: Content and marketing teams using agent workflows should treat text passed between agents as untrusted input and audit how those agents handle delegated tasks.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
Ars Technica: MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
Related on Z Media
- Google ships Gemini 4 Argon with tiered access and a price that doubles in NovemberOur brief, via Google DeepMind, 2 days ago
- OpenAI employee arrested over hidden recording device in officevia The Verge, 2 days ago
- YouTube Music starts labeling tracks made primarily with generative AIOur brief, via The Verge, yesterday
- Character.AI files for bankruptcy as Disney offers $20M for assets and a licenseOur brief, via TechCrunch, 3 days ago
- Anthropic warns small AI models could soon self-replicate across IoT devicesvia Ars Technica, 3 days ago
- Anthropic gives METR researchers employee-level access to its modelsvia TechCrunch, 6 hr ago