Security / AI Red Teaming
A hands-on kit for authorized red teaming of locally run LLMs, with jailbreak techniques, prompt-injection scenarios, streaming attack visualization, and support for OpenAI-compatible local model servers.
The page clearly describes a real AI-security project with a specific use case: testing jailbreaks and agent prompt injection against locally run, OpenAI-compatible models. The README gives enough detail for a public listing, including supported model families, quick-start steps, architecture notes, and a concrete explanation of what the lab demonstrates.
The snapshot does not show a demo, screenshots, or release history, so a visitor cannot tell how polished the UI is or how actively maintained the project is beyond the README and commit count.
Last evaluated 35 days ago. Current rank #655. Down 3 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.
