@mutmutco/claude-plugin@4.5.102
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe inspected source supports ordinary CLI behavior and limited, opt-out Hub telemetry. The scanner’s agent-configuration and credential-transfer hints do not establish an attack surface.
Decision evidence
public snapshot- package.json defines no lifecycle scripts and packages the CLI bundle as part of the product.
- The flagged agent-config logic classifies untracked configuration paths for Git cleanliness checks; it does not modify agent settings.
- CLI telemetry sends the command name, version, CI status, and operating system to the configured Hub, and can be disabled with MMI_TELEMETRY=off.
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@4.5.102.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.102 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.