sigmap@8.31.0
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-aiThis is not malicious install-time behavior, but the explicit setup command makes broad, behavior-bearing AI-agent configuration changes and adds persistence. The scanner claims of credential redirection and command-output exfiltration were not supported by the inspected source.