mcp-skill-sec is an open-source command-line auditing tool for MCP server skills and agent system prompts. It deterministically checks inputs against eight malicious-skill supply-chain patterns without using an LLM, for developers and security teams.
mcp-skill-sec is an AI & LLM security project. It focuses on detecting malicious supply-chain patterns in MCP server skills and agent system prompts. mcp-skill-sec is an open-source project aimed at AI developers and security engineers. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
It is developed by sudo-ai-git, and it first shipped in 2026. The project is developed in the open on GitHub with 16 commits in the last 90 days. Among its 6 catalogued features are MCP auditing, skill scanning, and prompt scanning. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do