@mutmutco/codex-plugin@4.5.137
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found no install-time execution or malicious behavior. The flagged agent-configuration location only classifies paths for git filtering, and the CLI telemetry sends limited product-use metadata with an opt-out.
Decision evidence
public snapshot- The package manifest declares no lifecycle scripts and packages the plugin manifest, skills, launcher, and CLI files.
- The plugin manifest describes MMI workflow skills and guarded hooks as product capabilities.
- The flagged agent-directory code classifies paths for git change filtering; it does not modify agent configuration.
- When an mmi-cli command runs, telemetry sends its command path, version, CI status, and OS to the configured MMI Hub endpoint; MMI_TELEMETRY=off disables this request.
- The telemetry uses the package’s default Hub endpoint unless MMI_HUB_URL is set.
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@4.5.137.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.137 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.