@mutmutco/codex-plugin@4.5.131
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiStatic inspection found no lifecycle hook or concrete attack behavior. The scanner’s agent-configuration indicator points to a path classifier used to prevent certain untracked agent files from being pushed, while the observed telemetry is limited to CLI metadata sent to the Hub endpoint.
Decision evidence
public snapshot- package.json has no lifecycle scripts or executable entrypoint declaration; it lists the plugin, skills, bin, and CLI files.
- The flagged agent-config paths are classified as uncommittable paths in a helper used to exempt untracked paths from push checks; this code does not write agent configuration.
- CLI telemetry sends the command name, package version, CI status, and operating system to the default Hub endpoint, and can be disabled with MMI_TELEMETRY=off.
- Hub API calls obtain a session token and send it to the configured Hub base URL for the requested board snapshot.
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@4.5.131.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.131 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.