@mutmutco/codex-plugin@4.5.170
MMI workflow skills and org gates delivery.
AI Security Review
scanned 6d ago · by lpm-firewall-aiSource inspection found no lifecycle hook or confirmed malicious behavior. The flagged agent-path logic is for git cleanliness checks, while CLI telemetry sends limited usage metadata to the Hub endpoint.
Decision evidence
public snapshot- package.json contains no lifecycle scripts; it packages the plugin, skills, and CLI.
- The flagged agent-directory code only exempts certain untracked paths during git cleanliness checks; it does not modify agent settings.
- When a CLI command runs, telemetry sends its command name, client version, CI status, and operating system to the configured Hub endpoint.
- The CLI entrypoint loads the main bundle for commands other than the version option.
- CLI-call telemetry is enabled unless MMI_TELEMETRY is set to off, but the inspected payload contains only basic command and environment metadata.
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@4.5.170.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.170 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.