@maxiaochao/pi-toolkit@0.11.6
Personal pi coding agent toolkit: scheduler, /btw, /cache_export, apply_patch, browser automation, and bundled theme/skills.
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe automatic postinstall write to a Pi agent configuration file is a guarded-scope agent integration risk. The inspected bundled content is general guidance, so this supports a warning rather than a block.
Decision evidence
public snapshot- package.json connects the postinstall hook to scripts/install-agents.mjs.
- The installer targets ~/.pi/agent/AGENTS.md and replaces it when its contents differ from the bundled file.
- The bundled file contains general coding guidance and says project-specific instructions override it.
- The installer only syncs the package’s bundled Pi guidance; the inspected text describes general coding practices.
Source & flagged code
15 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
packages/worktree/tests/extension.test.mjsView on unpkg · L57Findings
Affected versions and remediation
This report applies to @maxiaochao/pi-toolkit@0.11.6.
See all versions of @maxiaochao/pi-toolkit for other recorded verdicts.
- Review the evidence and your use of @maxiaochao/pi-toolkit@0.11.6 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.