sigmap@8.20.0
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 package exposes a local code-indexing API and CLI, with no install-time execution hook. The flagged network, tracking, and agent-configuration behaviors correspond to optional MCP output, local-only usage logging, or explicit setup actions; I found no attack chain that forwards credentials or unrelated command output.