@mutmutco/codex-plugin@4.5.119
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package has no install lifecycle hook, and the flagged agent path is used only by a Git cleanliness check. The observed telemetry and credential exchange are tied to user-invoked CLI and MMI Hub workflows, with no unrelated credential recipient or concrete attack behavior identified.
Decision evidence
public snapshot- package.json identifies this as an MMI workflow plugin and defines no lifecycle scripts.
- The flagged .codex path is part of a Git cleanliness check; only untracked agent configuration paths are exempted from blocking that check.
- After a user invokes a CLI command, the CLI sends the command name, version, CI status, and operating system to the MMI Hub; telemetry can be disabled with MMI_TELEMETRY=off.
- GitHub credentials are sent to the configured Hub's auth-session endpoint to obtain a Hub session; the default Hub endpoint is the package's MMI service.
- Usage telemetry is sent automatically for CLI commands unless disabled.
- The Hub session exchange sends a GitHub token to the configured Hub 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@4.5.119.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.119 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.