@mutmutco/codex-plugin@4.5.166
MMI workflow skills and org gates delivery.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package manifest has no install lifecycle hook, and the flagged agent path is part of Git safety classification. The inspected CLI telemetry sends limited invocation metadata to its MMI Hub endpoint, with an opt-out; no concrete attack behavior was established.
Decision evidence
public snapshot- package.json contains no lifecycle hook and packages the plugin, skills, launcher, and CLI.
- The flagged agent paths are directory names used by a Git path classifier, not agent configuration writes.
- CLI telemetry sends only the command, version, CI status, and operating system to the MMI Hub endpoint; it can be disabled with MMI_TELEMETRY=off.
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@4.5.166.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.166 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.