AI Security Review
scanned 3d ago · by lpm-firewall-aiNo confirmed malicious attack surface is established. The package is an explicitly invoked local AI-task cockpit that can run installed agent CLIs and user-defined workflow checks.
Decision evidence
public snapshot- package.json has only prepublishOnly; no install-time lifecycle hook.
- dist/core/backend-detect.js only probes existing CLIs; it does not install packages.
- dist/core/backend-detect.js reads a GitHub token but no package code consumes or transmits it.
- dist/index.js starts a local CLI/server only after explicit user invocation.
- dist/workflows/run.js runs configured agent/check commands in user-selected workflows and worktrees.
- No eval, dynamic module loading, credential exfiltration, or hidden persistence found in inspected source.
Source & flagged code
3 flagged · loading sourcePackage source references child process execution.
dist/core/claude-cli-runner.jsView on unpkg · L1This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/core/backend-detect.jsView on unpkgPackage source invokes a package manager install command at runtime.
dist/core/backend-detect.jsView on unpkg · L40