@mutmutco/claude-plugin@4.5.182
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package has no install lifecycle hooks, and the reviewed telemetry is limited to CLI usage metadata sent on command invocation. The agent configuration behavior is an explicit repair flow that restores existing marketplace pins, so the source does not establish malicious behavior.
Decision evidence
public snapshot- package.json contains no lifecycle scripts and identifies this as an MMI Hub package.
- The required CLI location reads Claude’s known marketplaces configuration and names the MMI marketplaces.
- CLI command telemetry sends the command name, package version, CI status, and operating system; it runs when a CLI command is invoked.
- The telemetry uses the configured Hub endpoint, with an AWS endpoint as the default.
- Plugin repair is driven by an explicit CLI heal command and restores previously captured marketplace pins.
- Telemetry is enabled unless MMI_TELEMETRY is set to off, but the inspected payload contains only command and environment metadata.
Source & flagged code
8 flagged · loading sourceSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
cli/dist/main.cjsView on unpkg · L39Source appears to send environment or credential material to an external endpoint.
cli/dist/main.cjsView on unpkg · L39Findings
Affected versions and remediation
This report applies to @mutmutco/claude-plugin@4.5.182.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.182 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.