codex-image
Warn
Audited by Snyk on Sep 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The agent skill reads local repositories, files, pasted briefs, and URLs (including potentially public URLs containing outsider-authored free text) via user input handling and web fetching without pre-selection of specific items by the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata