AI Security Review
scanned 3h ago · by lpm-firewall-aiLPM blocks this version under the AI-agent control-surface policy. Installing the package runs a lifecycle hook that launches a platform binary with `setup`. Package documentation states this setup installs an autostart daemon and agent-CLI plugins with hooks that alter agent tool behavior.
Decision evidence
public snapshot- `package.json` defines `postinstall: node postinstall.js`.
- `postinstall.js` automatically invokes `skyline setup` unless CI or an opt-out env var is set.
- `bin.js` resolves and runs a platform package binary with the `setup` argument.
- `README.md` states setup installs an autostart daemon and Skyline plugins for agent CLIs on PATH.
- `README.md` says the plugin uses hooks to constrain Claude built-in `Write`, `Edit`, and `Bash` tools.
- The JavaScript wrapper contains no credential harvesting, HTTP client, shell string, eval, or direct file writes.
- No executable platform binary is included in this extracted package, so its internal implementation was not inspectable.
Source & flagged code
3 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgSource fingerprint signature matches a known malicious package signature; route for source-aware review.
bin.jsView on unpkg