@mutmutco/codex-plugin@4.5.113
MMI workflow skills and org gates delivery.
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection found no lifecycle hook or credential exfiltration behavior. The scanner's credential and agent-configuration indicators resolve to bounded Hub telemetry, an explicitly enabled GitHub app flow, and a guard that excludes agent configuration from push checks.
Decision evidence
public snapshot- package.json contains package metadata and shipped-file declarations, with no install lifecycle script.
- Invoked CLI commands send command name, version, CI status, and platform to the MMI Hub telemetry endpoint; telemetry can be disabled with MMI_TELEMETRY=off.
- The flagged agent-configuration paths are excluded from push-wall blocking checks.
- App credentials are used only when MMI_ACTOR=app is set, for eligible commands, and the installation token request goes to api.github.com.
- The outbound telemetry contains bounded usage metadata, not environment variables or credential values.
- The flagged .codex path match protects agent configuration from being included in repository push handling.
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@4.5.113.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.113 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.