@mutmutco/codex-plugin@4.5.112
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found no lifecycle hook or confirmed credential exfiltration. The reported network behavior is user-triggered, limited usage telemetry to the package's Hub endpoint, and supports an opt-out.
Decision evidence
public snapshot- package.json defines the package files and has no lifecycle hook, so installation does not automatically run the CLI.
- The required agent-configuration location lists directories that the CLI treats as uncommittable configuration paths; its surrounding code filters those paths from commit eligibility.
- CLI-call telemetry sends only the command name, package version, a CI boolean, and operating system to the configured Hub telemetry route; it can be disabled with MMI_TELEMETRY=off.
- Telemetry is sent from the CLI pre-action hook when a command is invoked. The default Hub URL is configurable through MMI_HUB_URL.
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@4.5.112.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.112 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.