@mutmutco/codex-plugin@4.5.101
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install hooks, and the flagged agent-config code only filters untracked paths from a Git cleanliness check. The telemetry sends limited command metadata to the package's default Hub endpoint, with an opt-out; no concrete attack behavior was found.
Decision evidence
public snapshot- package.json contains no lifecycle scripts or dependencies.
- The flagged agent paths are used by a local Git cleanliness check; only untracked agent configuration paths are exempted from its blocking list.
- CLI telemetry sends the command name, version, CI status, and operating system to the Hub telemetry route.
- The telemetry runs from the CLI pre-action hook; its default Hub host is the package's API endpoint.
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/codex-plugin@4.5.101.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.101 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.