@mutmutco/claude-plugin@4.5.124
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found no install hook or concrete attack behavior. The scanner's agent-configuration hint points to Git status filtering, while the observed network activity is CLI telemetry and Hub API use.
Decision evidence
public snapshot- The root manifest lists plugin metadata, skills, launchers, and the CLI; it defines no npm lifecycle commands.
- The CLI entrypoint loads the bundled main file when a user runs a command.
- The flagged agent paths are checked to filter untracked files in Git status; this code does not write agent configuration.
- A CLI command sends its name, version, CI status, and operating system to the Hub; telemetry can be disabled with MMI_TELEMETRY=off.
- A Hub API call sends a bearer token to the configured Hub endpoint as part of a board request; the default endpoint is the Hub service.
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@4.5.124.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.124 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.