@mutmutco/codex-plugin@4.5.165
MMI workflow skills and org gates delivery.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package manifest has no lifecycle hooks. The inspected runtime behavior is limited to user-triggered CLI telemetry and a read-only agent-path check, with no concrete malicious behavior established.
Decision evidence
public snapshot- The root package manifest declares no install or other lifecycle scripts.
- The agent-configuration path check only exempts untracked agent configuration and session paths from a blocking-path check; it does not modify them.
- When a CLI command is invoked, telemetry sends only its command path, client version, CI status, and operating system, and supports an opt-out.
- Telemetry uses the configured MMI Hub URL or the package's default Hub endpoint.
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@4.5.165.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.165 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.