@mutmutco/codex-plugin@4.5.105
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package has no install lifecycle hooks, and the flagged agent-config path is used for path classification rather than configuration mutation. The inspected runtime telemetry is limited to CLI usage metadata sent to the package’s Hub during a user-run command, so no malicious behavior was established.
Decision evidence
public snapshot- package.json contains no lifecycle hooks.
- The CLI telemetry payload contains only the command, version, a CI boolean, and operating system; it can be disabled with MMI_TELEMETRY=off.
- Telemetry is sent from the CLI pre-action handler when a command runs, to the package’s default Hub endpoint.
- The hinted agent-config path is handled by a path-classification helper that normalizes and checks paths; the inspected code does not write agent configuration.
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@4.5.105.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.105 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.