MCPTox
PulseAugur coverage of MCPTox — every cluster mentioning MCPTox across labs, papers, and developer communities, ranked by signal.
-
New 'tool poisoning' vulnerability targets AI agents via MCP metadata
A new security vulnerability, dubbed "tool poisoning," has been identified within the Model Context Protocol (MCP), which allows AI agents to interact with various tools and resources. This attack involves embedding mal…
-
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…