Security / Developer Security Tool
Kernel-level read gate for AI coding agents that blocks protected file reads before bytes reach the agent, with Linux fanotify and macOS Endpoint Security support.
The page clearly presents a real AI-adjacent security tool with a specific job: controlling file reads for coding agents at the OS level. The README shows how it works, what platforms it supports, quick-start commands, architecture notes, and caveats about containment boundaries, which is enough for a useful public listing.
The snapshot does not show install/package status beyond examples and a brew tap mention, and it does not provide enough evidence about release maturity, test coverage, or how easy it is to set up end-to-end on each platform.
Last evaluated 5 days ago. Current rank #213. Up 2 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.
