@mutmutco/codex-plugin@4.5.107
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest has no install-time hook, and the flagged agent-related code only identifies paths for Git clean-tree handling. The inspected CLI telemetry sends limited usage metadata to the product's configured Hub, so no malicious behavior is established.
Decision evidence
public snapshot- package.json declares no lifecycle hooks or package entrypoints and ships the CLI files as package contents.
- The flagged agent-config location lists directories used to identify files excluded from a Git clean-tree check; it does not modify agent configuration.
- When a CLI command runs, telemetry sends its command path, version, CI status, and operating system to the configured MMI Hub; MMI_TELEMETRY=off disables it.
- The default telemetry destination is the package's MMI Hub endpoint, and the main bundle is loaded by the CLI launcher when invoked.
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@4.5.107.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.107 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.