codex
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents the OpenAI Codex CLI without including malicious patterns. It implements security guardrails by defaulting to "--sandbox read-only" and requiring user approval for powerful flags like "--sandbox workspace-write" or "--dangerously-bypass-approvals-and-sandbox". No unauthorized data exfiltration, hardcoded credentials, or obfuscated content was found. Interactions with the Codex CLI are consistent with its primary purpose as an external tool from a well-known service.
Audit Metadata