codex-imagegen

Warn

Audited by Snyk on Jul 5, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The required runtime workflow runs codex exec with a user-supplied free-form prompt; that prompt is outsider-authored text (the operating user’s message) being fed into the agent/LLM context, creating indirect prompt-injection exposure.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 5, 2026, 07:17 AM
Issues
1
Security Audit — snyk — codex-imagegen