oh-my-codex@0.21.32
Multi-agent orchestration layer for OpenAI Codex CLI
AI Security Review
scanned 13d ago · by lpm-firewall-aiThe inspected behavior supports a warning for first-party agent setup capability, not a confirmed malicious install hook. Setup is user-invoked and the reviewed postinstall path returns without action for local installs.
Decision evidence
public snapshot- The install hook calls postinstall.js, but local installs return without action; the reviewed hook does not run the setup command. [c_5d1e2e60f3083660_1, c_5d1e2e60f3083660_2]
- The CLI exposes setup as an explicit command. That command can generate native agent configuration and write managed content to its destination. [c_5d1e2e60f3083660_3, c_5d1e2e60f3083660_4, c_5d1e2e60f3083660_5, c_5d1e2e60f3083660_6]
- Plugin-mode setup has an interactive prompt to install or update its AGENTS.md defaults. [c_5d1e2e60f3083660_7]
- The reviewed setup behavior is explicitly user-invoked, and plugin-mode AGENTS.md installation has a prompt; the inspected source did not establish an unconsented install-time configuration change.
Source & flagged code
11 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@0.21.32.
See all versions of oh-my-codex for other recorded verdicts.
- Review the evidence and your use of oh-my-codex@0.21.32 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.