oh-my-codex@0.21.14
Multi-agent orchestration layer for OpenAI Codex CLI
AI Security Review
scanned 19d ago · by lpm-firewall-aiSource inspection found first-party agent configuration written by the explicit setup command, which warrants a capability warning. The postinstall path does not invoke setup, and no concrete malicious behavior was established.
Decision evidence
public snapshot- The postinstall hook returns early for local installs and hydrates the native runtime only for global installs.
- Agent configuration is written through the explicit setup command, which generates first-party TOML files from the package’s prompt files.
- The flagged integration locations are tests or configuration inventory code; they do not establish an automatic install-time agent configuration change.
- The inspected lifecycle path does not call setup; it hydrates the runtime and records an install version.
- Native agent configuration writing is reached through the setup command, not the package install hook.
Source & flagged code
13 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@0.21.14.
See all versions of oh-my-codex for other recorded verdicts.
- Review the evidence and your use of oh-my-codex@0.21.14 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.