@mutmutco/claude-plugin@4.5.183
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package manifest has no install lifecycle scripts or runtime dependencies. The inspected agent-configuration behavior is limited to checking marketplace settings and preserving existing pins during explicit repair; telemetry contains only command metadata and has an opt-out.
Decision evidence
public snapshot- package.json declares no lifecycle scripts or runtime dependencies.
- The inspected agent integration reads Claude marketplace settings and resolves whether auto-updates are enabled; it does not itself enable them.
- Marketplace pins are captured and restored during plugin repair, which is exposed through an explicit CLI command.
- When a CLI command runs, telemetry sends only its command name, version, CI status, and operating system to the package's default Hub; MMI_TELEMETRY=off disables it.
- The GitHub token exchange is a bearer-authenticated request to the Hub API's session 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@4.5.183.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.183 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.