@mutmutco/claude-plugin@4.5.180
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the inspected runtime network behavior is limited to Hub authentication and command-use telemetry. The marketplace configuration path is used by an explicit CLI repair flow, not an install-time mutation.
Decision evidence
public snapshot- package.json contains no lifecycle scripts or executable entrypoint; it lists plugin, skill, launcher, and CLI files.
- The CLI defaults to its Hub host, and its GitHub bearer token is sent to that host's session-authentication endpoint.
- CLI telemetry sends only the command name, version, CI status, and operating system to the configured Hub; it can be disabled with MMI_TELEMETRY=off.
- The agent marketplace repair path is invoked by CLI commands; the doctor repair runs only in its full mode.
- The cited marketplace path is used to preserve the MMI and Jerv marketplace settings during that repair.
- CLI-call telemetry is enabled by default unless the opt-out is set.
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@4.5.180.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.180 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.