@mutmutco/claude-plugin@4.5.178
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install hooks, and the flagged marketplace code reads existing configuration to assess update status. The inspected network behavior supports the package's CLI and Hub workflows, with no concrete attack behavior established.
Decision evidence
public snapshot- The package manifest defines no install lifecycle scripts and includes the CLI and plugin files.
- The reported marketplace location is a configuration path; nearby logic reads marketplace declarations to determine auto-update status.
- Marketplace auto-update status follows existing user or settings declarations, and plugin repair is exposed as a CLI command.
- The CLI uses an existing GitHub token in a session exchange with the configured MMI Hub endpoint; the source shows no unrelated credential recipient.
- CLI telemetry sends the invoked command, package version, CI status, and operating system to the Hub endpoint, with an environment opt-out.
- The default Hub URL is the package's configured service endpoint.
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@4.5.178.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.178 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.