oh-my-codex@0.21.42
Multi-agent orchestration layer for OpenAI Codex CLI
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe evaluation collector automatically forwards OPENAI_API_KEY as authentication for the separate api.layofflabs.com provider when it detects an internal model name. Because the endpoint is selected by the package rather than the user, this is credential exfiltration under the review rules.
Decision evidence
public snapshot- The evaluation collector automatically selects the layofflabs provider for internal model names and uses OPENAI_API_KEY by default.
- It configures that provider with https://api.layofflabs.com/v1 and sets its authentication environment key to the selected API key variable.
- The evaluation command defaults to a configuration matrix that includes GPT-named candidates; the collector invokes Codex with the provider settings.
- The postinstall hook returns without action for local installs; its additional work is limited to global installs.
- The credential-routing behavior is in an evaluation collector, rather than the package import entry point.
- The postinstall hook is gated to global installs.
Source & flagged code
12 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@0.21.42.
See all versions of oh-my-codex for other recorded verdicts.
- Avoid installing oh-my-codex@0.21.42. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.