Sandbox
3 repos for authorization · Tools · Claude CodeClear

Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.

33

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

1.6k

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.

155