@mutmutco/codex-plugin@4.5.173
MMI workflow skills and org gates delivery.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install lifecycle hooks, and the inspected runtime telemetry is limited to CLI metadata sent to the MMI Hub endpoint. The targeted marketplace code reads marketplace settings; the inspected source does not establish a concrete attack.
Decision evidence
public snapshot- package.json declares no install lifecycle hooks.
- The targeted bundle location identifies Claude’s marketplace registry path and reads marketplace settings.
- On CLI command use, telemetry sends the command name, version, CI status, and operating system; the recipient is the configured MMI Hub endpoint.
- The telemetry call is attached to CLI command handling, not package installation.
- The bundle identifies the MMI Hub endpoint and permits an environment override.
- The inspected source shows no confirmed credential theft, unrelated data transfer, or unconsented agent configuration change.
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/codex-plugin@4.5.173.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.173 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.