@maxiaochao/pi-toolkit@0.2.2
Personal pi coding agent toolkit: /todos, /btw, /cache_export extensions, browser automation, and bundled theme/skills.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe automatic postinstall write can change Pi agent instructions, so a warning is appropriate under the agent extension lifecycle policy. The inspected behavior supports a guarded capability warning, not a confirmed malicious attack.
Decision evidence
public snapshot- The postinstall hook automatically runs the agent setup script during installation.
- The script targets the user's Pi agent directory and loads this package's bundled instructions.
- When the existing agent instructions differ, the script replaces them with the bundled file.
- The write is limited to Pi's agent directory and uses instructions bundled with this package.
- The script does not send data over the network or launch a remote payload.
Source & flagged code
4 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgThe postinstall hook automatically runs the agent setup script during installation.
package.jsonView on unpkg · L50Findings
Affected versions and remediation
This report applies to @maxiaochao/pi-toolkit@0.2.2.
See all versions of @maxiaochao/pi-toolkit for other recorded verdicts.
- Review the evidence and your use of @maxiaochao/pi-toolkit@0.2.2 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.