@mutmutco/claude-plugin@4.5.151
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection did not confirm the scanner's credential exfiltration claim: the reviewed telemetry request contains usage metadata, and the flagged agent-path code classifies paths rather than changing agent settings. The manifest has no lifecycle scripts.
Decision evidence
public snapshot- package.json contains no lifecycle scripts; it ships a plugin and CLI.
- The flagged agent path location classifies agent configuration directories for Git push filtering; it does not write agent settings.
- CLI call telemetry sends the command, version, CI status, and operating system to the Hub when the CLI runs; MMI_TELEMETRY=off disables it.
- The telemetry endpoint uses the MMI Hub URL, defaulting to the package's Hub host.
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@4.5.151.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.151 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.