{"owner":"Pantheon-Security","github":"https://github.com/Pantheon-Security","claimed":false,"inventory":[],"indexed":[{"repo":"Pantheon-Security/medusa","github":"https://github.com/Pantheon-Security/medusa","description":"AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.","language":"Python","stars":963,"topics":["devsecops","open-source","python","sast","scanner","security","static-analysis","vulnerability-scanner","ai-security","code-analysis"],"license":"AGPL-3.0","category":"security-tools"},{"repo":"Pantheon-Security/notebooklm-mcp-secure","github":"https://github.com/Pantheon-Security/notebooklm-mcp-secure","description":"Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 17 security hardening layers","language":"TypeScript","stars":79,"topics":["ai","automation","browser-automation","claude","google","llm","mcp","model-context-protocol","notebooklm","open-source"],"license":"MIT","category":"mcp-servers"}],"how_to_buy":"GET /r/Pantheon-Security/<repo> (Accept: application/json) for any listed repo here: tree, README, price and the checkout to pay (x402; rehearse first at its test twin, simulated money). Repos under 'indexed' are free: clone them from GitHub."}