codex-imagegen
Warn
Audited by Snyk on Aug 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). SKILL.md describes running
codex exec ... '<...design brief...>'where the only readable free text ingested at runtime is the user-provided generation prompt; there is no required workflow step that fetches or monitors outsider-authored content from emails, tickets, feeds, issues, or arbitrary posted text sources without the user first supplying a specific prompt.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata