sigmap@8.54.2
The deterministic, verifiable grounding layer for AI code work — a zero-dependency signature-and-evidence map that grounds Claude, Cursor, Copilot, Aider, Windsurf, local LLMs & MCP agents against your real code (repo + installed libraries) so they stop h
AI security review
scanned · by lpm-firewall-aiThe flagged behaviors are tied to user-invoked setup or an optional context adapter, and the inspected sources do not show an active attack chain. The manifest has no install lifecycle hook, and the Willow request sends project context rather than credentials.