@mutmutco/claude-plugin@4.5.112
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThis warrants a warning because a custom MMI_HUB_URL can receive an existing GitHub token during session exchange. The default points to the product Hub, and the manifest has no install lifecycle hook, so the inspected behavior does not support blocking the package as malicious.
Decision evidence
public snapshot- The flagged agent directories are exempted from git-clean blocking only when untracked; this helper does not configure or write agent settings.
- The package manifest defines no lifecycle scripts.
- GitHub credentials can come from environment variables or the local gh authentication command.
- MMI_HUB_URL overrides the Hub destination, and the source only strips a trailing slash; its default is the product Hub endpoint.
- When no Hub token override or valid cached session is available, Hub authentication sends the existing GitHub token as a bearer token to the selected endpoint. Hub API helpers and the whoami command reach this flow.
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@4.5.112.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.112 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.