Vulnerability in agents from Google and others exposes structural flaw in MCP
Trust gaps in the new protocol spread malicious prompts from one agent to another.
https://arstechnica.com/security/2026/10/vulnerability-in-agents-from-google-and-others-exposes-structural-flaw-in-mcp/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social
