3 projects
weightguard
Multi-format security scanner for ML model artifacts: pickle/PyTorch (incl. zip-container), NumPy, Joblib, Keras Lambda-layer, ONNX custom-op, and GGUF header checks.
aisecscan
Static security scanner for Claude Code configs (.claude/, .mcp.json, CLAUDE.md), MCP servers, subagents, and skills. Cursor, Copilot, Windsurf, Cline, LLM app-code, and AI supply-chain checks are on the roadmap.
agentscanner
Static security scanner for agentic AI configuration: settings, permissions, hooks, MCP servers, agents, skills, and steering files (Checkov for AI agent stacks).
