@mutmutco/codex-plugin@4.5.164
MMI workflow skills and org gates delivery.
AI Security Review
scanned 7d ago · by lpm-firewall-aiSource inspection found no install-time behavior or concrete attack. The scanner's credential and agent-configuration signals resolve to a Hub session exchange and Git path filtering, respectively.
Decision evidence
public snapshot- The root manifest identifies the MMI Hub plugin, includes the CLI files, and declares no lifecycle script.
- The CLI exposes mmi-cli and loads its main bundle when the command is invoked.
- The agent-directory match is used to exempt untracked paths from commit blocking; it does not modify agent settings.
- The Hub session flow obtains a GitHub token and submits it as a bearer token to the Hub authentication endpoint.
- The default Hub endpoint is an MMI service, consistent with the package's MMI Hub identity.
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@4.5.164.
See all versions of @mutmutco/codex-plugin for other recorded verdicts.
- Review the evidence and your use of @mutmutco/codex-plugin@4.5.164 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.