oh-my-codex@0.21.45
Multi-agent orchestration layer for OpenAI Codex CLI
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe install hook is gated to global installs and hydrates the package's native runtime, which is consistent with the tool's purpose. The eval collector's automatic use of OPENAI_API_KEY with a third-party provider creates a real credential-handling risk, so this version warrants a warning rather than a publish block.
Decision evidence
public snapshot- The eval collector uses OPENAI_API_KEY for a provider it automatically selects as layofflabs, whose API base URL is https://api.layofflabs.com/v1.
- The postinstall hook does nothing for non-global installs; for global installs it hydrates the package's native runtime.
- Native runtime assets are fetched using the package repository's release configuration.
- The package describes itself as a Codex CLI orchestration tool, and its main and bin point to the expected dist entry points.
- The prepare script exits if the package's built entry points already exist; otherwise it bootstraps dependencies with scripts disabled and builds the package.
- The collector is an eval utility that clones the package's own repository at a configured revision; the reviewed source does not show it running at import or install time.
Source & flagged code
23 flaggedInstall-time lifecycle script matches a deterministic static-gate block pattern.
package.jsonView on unpkgPackage defines install-time lifecycle scripts.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to oh-my-codex@0.21.45.
See all versions of oh-my-codex for other recorded verdicts.
- Review the evidence and your use of oh-my-codex@0.21.45 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.