medusa-security is an open-source, AI-first security scanner designed for codebases, LLM agents, and RAG pipelines. It features 79 analyzers, 40,000+ detection patterns, and prompt injection detection, helping security engineers and AI developers identify vulnerabilities quickly.
medusa-security sits in PulseGate's Security & compliance platforms category. It focuses on detecting security vulnerabilities in AI/ML codebases, LLM agents, and RAG pipelines efficiently. It is built as an open-source project for security engineers and AI developers. medusa-security is open source under the AGPL-3.0 license. It runs on the web and the command line, and it can be self-hosted.
Pantheon Security builds and maintains medusa-security, and it first shipped in 2025. The project is developed in the open on GitHub with 604 stars and 75 commits in the last 90 days. Among its 7 catalogued features are AI security scanning, 79 analyzers, and 40,000+ detection patterns.
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