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 108 days ago. Current rank #739. 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.
An AI harness for long-running penetration tests, bug bounties, and code audits. It combines specialist agents, a Kali runtime, durable state, and second-agent verification for findings.
Open-source security agent framework for cloud, code, and runtime. It ships 45 built-in agents for AWS, GCP, Azure, Kubernetes, GitHub, and GitLab, and lets users create custom agents in a single markdown file.
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.
