MCPTox
PulseAugur coverage of MCPTox — every cluster mentioning MCPTox across labs, papers, and developer communities, ranked by signal.
-
Microsoft warns of AI agent data theft via poisoned tool descriptions
Microsoft has issued a warning about a security vulnerability in Model Context Protocol (MCP) tools, dubbed "MCP tool description poisoning." Attackers can embed hidden instructions within the natural-language metadata …
-
AI Agent Protocol MCP Faces Critical Supply Chain Security Flaw
A significant security vulnerability has been discovered in the MCP (Meta-Communication Protocol) ecosystem, which is widely used to connect AI agents to external tools. The vulnerability, dubbed CVE-2025-53967, allows …
-
IntentProbe scans AI model brains for malicious tool descriptions
A new tool called IntentProbe has been released, offering a novel approach to detecting malicious AI tool descriptions. Unlike traditional text-based scanners or LLM-as-judge methods, IntentProbe analyzes the internal a…