@mutmutco/codex-plugin@4.5.145
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found no install hook or concrete malicious behavior. Automatic telemetry is limited to command and environment metadata sent to the package Hub, while credential minting and file upload are tied to explicit configuration or commands.
Decision evidence
public snapshot- The package manifest has no install lifecycle scripts.
- The agent configuration paths are excluded only when checking untracked files for local repository cleanliness.
- Each CLI command sends its name, version, CI status, and operating system to the configured Hub endpoint; telemetry can be disabled with MMI_TELEMETRY=off.
- GitHub App token minting requires explicit app mode and sends a short-lived authorization request to GitHub.
- File upload requires an explicit tenant artifact command and a caller-supplied path.
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@4.5.145.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.145 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.