@mutmutco/codex-plugin@4.5.177
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe manifest defines no install hook, and the flagged integration location does not establish an automatic Codex configuration change. The observed telemetry is limited to CLI command metadata and is sent after a command is invoked.
Decision evidence
public snapshot- package.json contains no lifecycle scripts; it lists the plugin, skills, launcher, and CLI files.
- The flagged agent-integration location points to Claude marketplace paths and read helpers, not an automatic Codex configuration write.
- CLI-call telemetry runs when a command is invoked and sends the command name, version, CI status, and operating system to the configured MMI Hub; it can be disabled with MMI_TELEMETRY=off.
- The bundled CLI uses the MMI Hub endpoint by default, and its ordinary secret commands load Hub configuration before acting.
Source & flagged code
8 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@4.5.177.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.177 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.