Show HN: AI Agent Audit for Free

Category: security

Tags: security-scanner, ai-agent-security, mcp-server

Score: 7.5/10 (Innovation: 7, Technical: 8, Documentation: 8, Utility: 7)

This project is a security scanner for AI agents and MCP (Model Context Protocol) servers, providing vulnerability detection, package hallucination checking, and prompt injection protection. It stands out for its dual lightweight and enterprise versions, integration with major AI coding tools like Claude Code and Cursor, and its novel focus on securing the emerging AI agent ecosystem.

Target audience: backend devs, devops, security engineers

Repository: https://github.com/sinewaveai/agent-security-scanner-mcp · JavaScript · MIT · 113 stars

View on Hacker News