Trail of Bits skills for security research, vulnerability detection, and audit workflows

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills b…

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets on worktrees, across your Mac and any Linux box.

MCP server providing read-only access to Quicken For Mac financial data via Claude