@mutmutco/codex-plugin@4.5.142
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install or import lifecycle hook, and the flagged agent path code is a workspace cleanliness classifier rather than an agent configuration write. The runtime telemetry is limited to CLI usage metadata sent to the product Hub, while GitHub credentials follow the GitHub API client path.
Decision evidence
public snapshot- package.json contains package metadata and no lifecycle scripts.
- The flagged agent path code classifies configuration paths for a workspace cleanliness check; it does not mutate agent settings.
- A CLI command invocation sends command name, version, CI status, and operating system to the MMI Hub telemetry endpoint; the telemetry function supports an opt-out and sends no credentials in its payload.
- GitHub tokens are read from process environment or the GitHub CLI, and the client uses the configured GitHub API origin or api.github.com for bearer-authenticated requests.
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@4.5.142.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.142 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.