Loading npm security reports…
AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot - setup audits, guardrails, structured skills, deny hooks, and persistent learning loops.
LPM treats this as warn-only first-party agent extension lifecycle risk. No install-time attack occurs. Explicit install/setup commands write first-party AI-agent configuration and hook files into the selected project; the dashboard exposes a local terminal surface when invoked.
Package source references a known benign dynamic code generation pattern.
dist/dashboard/alpine.jsView on unpkg · L4Package source references dynamic require/import behavior.
scripts/warn-node-pty.mjsView on unpkg · L5Package ships non-JavaScript build or shell helper files.
workflow/install-goat-flow.shView on unpkgPackage source references a known benign dynamic code generation pattern.
dist/dashboard/alpine.jsView on unpkg · L4Package ships non-JavaScript build or shell helper files.
workflow/install-goat-flow.shView on unpkgPackage source references dynamic require/import behavior.
scripts/warn-node-pty.mjsView on unpkg · L5