@mutmutco/claude-plugin@4.5.171
MMI workflow skills and org gates delivery.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install hooks, the flagged agent paths are used for change detection, and the inspected network behavior is limited to Hub session authentication and basic command telemetry. The source does not establish a concrete attack surface.
Decision evidence
public snapshot- package.json contains no lifecycle scripts and packages the CLI bundle.
- The flagged agent paths are checked as project paths and exempted from untracked-change blocking; the code does not mutate agent configuration there.
- When a CLI command runs, telemetry sends only the command name, version, CI status and operating system; the user can disable it with MMI_TELEMETRY=off.
- The telemetry destination is the configured MMI Hub endpoint. The GitHub token exchange also sends the token to that Hub’s /auth/session endpoint for a Hub session.
Source & flagged code
7 flagged · loading sourceSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
cli/dist/main.cjsView on unpkg · L39Source appears to send environment or credential material to an external endpoint.
cli/dist/main.cjsView on unpkg · L39Findings
Affected versions and remediation
This report applies to @mutmutco/claude-plugin@4.5.171.
See all versions of @mutmutco/claude-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/claude-plugin@4.5.171 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.