@mutmutco/codex-plugin@4.5.144
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package has no install lifecycle script, and the flagged agent-directory code only classifies untracked Git paths. The CLI sends limited usage telemetry to its MMI Hub endpoint; the inspected telemetry path does not transfer credentials or command output.
Decision evidence
public snapshot- package.json declares no lifecycle scripts and ships the plugin, skills, launcher, and CLI files.
- The flagged agent-directory code only classifies untracked Git paths; it does not mutate agent configuration.
- Each CLI command triggers telemetry containing the command, version, CI indicator, and operating system, with an opt-out; the destination is the MMI Hub endpoint.
- CLI usage telemetry is sent by default, but the inspected payload contains no credentials or command output.
Source & flagged code
7 flagged · loading sourceSource appears to send environment or credential material to an external endpoint.
cli/dist/main.cjsView on unpkg · L39This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
cli/dist/main.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @mutmutco/codex-plugin@4.5.144.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.144 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.