@mutmutco/claude-plugin@4.5.104
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest declares no lifecycle hooks. Inspected bundled behavior is consistent with CLI telemetry and a user-invoked update flow, and the agent-path finding concerns filtering untracked paths rather than changing agent settings.
Decision evidence
public snapshot- package.json contains no lifecycle scripts and ships the plugin and CLI files.
- The agent configuration paths are used to exempt untracked agent settings from a Git cleanliness check; the inspected code does not modify them.
- CLI telemetry sends the invoked command, version, CI status, and operating system to the configured MMI Hub, with an environment opt-out.
- The CLI self-update flow installs @mutmutco/cli only when a user-invoked train command finds the CLI stale.
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@4.5.104.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.104 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.