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
Allowed — no malicious behavior detected
19 low-signal patterns reviewed and cleared.
AI security review
scanned · by lpm-firewall-ai
Source inspection found no install-time attack or confirmed malicious behavior. The flagged agent configuration and network behavior are user-invoked or caller-configured product functions.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Explicitly invoking the relevant setup, install, or Willow adapter functionality.
Impact
No confirmed malicious effect or covert credential forwarding was established.
Mechanism
The inspected code writes SigMap configuration or sends signature atoms to the configured Willow MCP endpoint.
Decision evidence
public snapshot
Evidence for AI clean decision
package.json exposes CLI entrypoints; its prepublishOnly command runs checks and does not declare an install lifecycle hook.
The flagged setup branch runs only when --setup is explicitly supplied; skill installation is also behind an explicit install command.
The inspected Claude and Codex adapter locations concern generated project guidance, and the Claude allowlist text says the user must add it to activate.
MCP client installation writes a SigMap server entry to the selected client configuration; the client targets are defined in source.
Skill installation writes generated skills to client-specific files; plain installation selects clients with an existing client artifact.
The Willow adapter takes its destination from caller options or WILLOW_MCP_URL and POSTs signature atoms to that destination; no package-controlled fixed gateway was found.
Automated scan signals; the review checked them and cleared this version. Where they are, most severe file first. Code opens a file's flagged lines, with their evidence, below.
Manifest-reachable source captures an API credential, sends it to a fixed unofficial gateway, and persists that redirection in agent or shell configuration.
gen-context.js
'Add the `permissions.allow` array above to `.claude/settings.json` to activate.',