Security / AI Security / Prompt Injection Defense
Open-source input scanner for AI agents that strips hidden instructions and scans text, files, images, PDFs, QR codes, audio, and video before they reach an agent.
The page clearly describes a real AI security tool with concrete capabilities, install steps, CLI usage, and Python integration examples. It explains what the scanner covers, what threats it catches, and how it fits into an agent pipeline, giving enough evidence for a useful public listing.
The crawl shows strong README detail, but visitors still cannot tell the project’s maturity beyond GitHub stats and a few usage snippets. There’s no visible release history, support policy, or side-by-side comparison showing how it performs against other guard tools.
Last evaluated 39 days ago. Current rank #818. 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.
