@mutmutco/claude-plugin@4.5.143
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe inspected source does not support the scanner’s malicious verdict: the manifest has no install hook, the agent-related location is a path classifier, and the network code serves the CLI’s Hub and GitHub operations. Mark clean.
Decision evidence
public snapshot- package.json defines the package and version but contains no lifecycle hook that runs during installation.
- The flagged agent configuration location is part of a path classifier that recognizes agent directories; the inspected code does not mutate those configurations.
- The CLI has a default MMI Hub endpoint and a GitHub client that uses the GitHub API origin and a supplied token for requests.
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@4.5.143.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.143 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.