@mutmutco/codex-plugin@4.5.132
MMI workflow skills and org gates delivery.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe manifest defines no install hooks, and the flagged agent integration location performs path classification rather than configuration mutation. The scanner’s network and process findings do not establish harmful behavior in the inspected source.
Decision evidence
public snapshot- package.json has no lifecycle hooks and publishes the plugin, skills, launcher, and CLI files.
- The flagged agent path logic only classifies agent configuration paths when checking untracked files; it does not modify agent configuration.
- The CLI launcher runs the main bundle for ordinary commands and handles version requests directly.
- The bundled CLI contains network and process execution code, but the inspected package entrypoints and flagged agent path logic show no concrete attack behavior.
Source & flagged code
7 flagged · loading sourceSource appears to send environment or credential material to an external endpoint.
cli/dist/main.cjsView on unpkg · L39This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
cli/dist/main.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @mutmutco/codex-plugin@4.5.132.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.132 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.