@mutmutco/codex-plugin@4.5.120
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest defines no install lifecycle hook, and the flagged agent-related code only filters Git status. CLI telemetry sends limited metadata to the package's configured MMI Hub endpoint, with an environment-variable opt-out; no concrete attack behavior was found.
Decision evidence
public snapshot- package.json contains no lifecycle scripts; it packages a CLI, plugin manifest, skills, and bin files.
- The flagged agent-configuration location defines paths used to exempt untracked agent configuration from push-wall blocking; it does not modify agent configuration.
- CLI telemetry sends the command name, version, CI status, and operating system to the configured MMI Hub URL; MMI_TELEMETRY=off disables it.
- The telemetry recipient defaults to the package's MMI Hub endpoint.
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@4.5.120.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.120 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.