oh-my-codex@0.21.7
Multi-agent orchestration layer for OpenAI Codex CLI
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe postinstall handler limits its behavior to global installs, runtime hydration, and an install stamp; it describes setup as explicit opt-in. The CLI setup path has a concrete first-party agent configuration capability, so this warrants a warning under the agent integration policy, but the inspected evidence does not show an automatic install-time control-surface attack.
Decision evidence
public snapshot- The postinstall hook loads its handler, but local installs exit without running setup.
- The CLI passes explicit arguments to its command handler, and setup can write managed agent configuration when invoked.
- Setup asks before overwriting an existing AGENTS.md unless an explicit force option is used.
- The global-install postinstall path hydrates a native runtime and records the installed version; it does not itself invoke setup.
- The inspected setup code backs up managed content before writing it and supports dry-run behavior.
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@0.21.7.
See all versions of oh-my-codex for other recorded verdicts.
- Review the evidence and your use of oh-my-codex@0.21.7 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.