@mutmutco/claude-plugin@4.5.152
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no lifecycle hooks or runtime entrypoint, and the flagged agent-path code only classifies Git changes. The inspected telemetry sends limited command metadata to the package’s Hub and has an opt-out; no concrete attack behavior was established.
Decision evidence
public snapshot- package.json declares no lifecycle scripts or runtime entrypoint.
- The flagged agent paths are checked to identify untracked configuration files that should block a Git workflow.
- CLI telemetry sends the invoked command, version, CI status, and operating system to the configured Hub; it can be disabled with MMI_TELEMETRY=off.
- The default Hub endpoint is the package’s MMI service.
- CLI telemetry is sent automatically unless explicitly disabled, but the inspected payload contains command and environment metadata rather than credentials or file contents.
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@4.5.152.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.152 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.