@maxiaochao/pi-toolkit@0.11.15
Personal pi coding agent toolkit: scheduler, /btw, /cache_export, apply_patch, browser automation, and bundled theme/skills.
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe postinstall hook makes an automatic change to global agent instructions, which warrants a warning under the first-party agent setup policy. The inspected behavior does not establish a malicious attack or support blocking publication.
Decision evidence
public snapshot- The manifest runs scripts/install-agents.mjs as a postinstall hook.
- The installer copies the package’s global AGENTS.md into ~/.pi/agent/AGENTS.md when that file is missing or differs.
- The copied file contains behavioral guidelines for an AI coding agent.
- The same installer installs this package’s pi-worktree CLI under the user’s home directory.
- The agent instructions are bundled with this toolkit, and the installer also sets a default theme and installs the toolkit’s own CLI.
- The inspected setup code does not show credential collection or a network transfer.
Source & flagged code
14 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@0.11.15.
See all versions of @maxiaochao/pi-toolkit for other recorded verdicts.
- Review the evidence and your use of @maxiaochao/pi-toolkit@0.11.15 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.