@mutmutco/claude-plugin@4.5.138
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the requested agent-config code only filters repository paths. The flagged outbound behavior is limited to MMI Hub usage telemetry, with an opt-out and no inspected credential transfer.
Decision evidence
public snapshot- package.json contains no lifecycle scripts and identifies the published CLI as package content.
- The agent-config match only identifies paths that a repository push-wall check exempts; it does not mutate agent settings.
- CLI telemetry sends the command path, version, CI status, and operating system to the default MMI Hub endpoint; MMI_TELEMETRY=off disables it.
- Telemetry is called from the CLI command pre-action hook. The inspected source showed no credential or command-argument transfer in this request.
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@4.5.138.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.138 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.