codex
Warn
Audited by Snyk on Feb 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's workflow instructs running "npx @openai/codex exec --full-auto", which at runtime fetches and executes remote npm package code (see https://www.npmjs.com/package/@openai/codex), so external code is executed and relied upon.
Audit Metadata