@maxiaochao/pi-toolkit@0.9.1
Personal pi coding agent toolkit: /todos, /btw, /cache_export and apply_patch extensions, browser automation, and bundled theme/skills.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe automatic hook modifies Pi's own global agent configuration without prompting, so the package warrants a warning for agent extension lifecycle risk. The inspected behavior does not establish an attack against a foreign or broad agent control surface.
Decision evidence
public snapshot- The package runs an automatic postinstall setup script.
- The setup script writes the bundled AGENTS.md into the Pi agent configuration directory without prompting, replacing different existing contents.
- For settings, the script adds a default theme only when one is missing; it does not replace a selected theme.
- The same hook installs this package's pi-worktree command and shell completion into the user's local bin directories.
- The agent configuration write is limited to Pi's own agent directory and uses this package's bundled file.
- The inspected browser test uses a temporary profile and communicates with a local debugging endpoint.
Source & flagged code
10 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
extensions/cache-export/tests/e2e-browser.mjsView on unpkg · L12Findings
Affected versions and remediation
This report applies to @maxiaochao/pi-toolkit@0.9.1.
See all versions of @maxiaochao/pi-toolkit for other recorded verdicts.
- Review the evidence and your use of @maxiaochao/pi-toolkit@0.9.1 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.