Security / AI Security / Red Teaming
Open-source security research tool for auditing Python AI agents and codebases with AST analysis and Docker-based runtime verification.
The page clearly describes an AI-adjacent developer tool with a specific purpose: finding vulnerabilities in Python AI agent codebases. It shows how the engine works, what it checks, how to install it, and how to run it, which makes it suitable for a public directory listing. The repository also includes benchmark notes, CI/CD workflow support, and concrete security use cases.
The crawl does not show the actual scan output format, a demo example, or enough detail to compare results across different projects. It also leaves questions about current maintenance and whether the listed benchmark numbers reflect reproducible tests on the repository.
Last evaluated 35 days ago. Current rank #803. Down 6 spots in the rankings.
Open-source security scanner for AI agents, MCP servers, and agent skills. It auto-discovers installed agent components and checks them for prompt injection, tool poisoning, secrets, malware payloads, and related risks.
Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.
GitHub Marketplace app from NeuraLegion that scans apps and APIs for vulnerabilities, proposes fixes, and validates remediations inside GitHub workflows.
Belay is an open-source, local-first security layer for AI coding agents. It blocks dangerous commands, secret leaks, prompt injection, and risky MCP tool calls, with human approval flows and support for multiple agents.
