@mutmutco/claude-plugin@4.5.139
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found package-aligned CLI telemetry containing command metadata and a GitHub token flow for the GitHub API client. The flagged agent-path code only classifies untracked paths; the scanner’s credential-exfiltration claim was not supported by the inspected flows.
Decision evidence
public snapshot- package.json contains no lifecycle scripts, and the package describes MMI workflow skills and organization gates.
- The flagged agent paths are checked when classifying untracked files; this code does not mutate agent configuration.
- CLI telemetry sends the command, version, CI status, and operating system to the configured MMI Hub, with an environment-variable opt-out.
- GitHub tokens are read for the GitHub API client, whose default destination is api.github.com.
- The inspected credential flow uses a GitHub API bearer token; the source does not show it being sent to the telemetry 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/claude-plugin@4.5.139.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.139 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.