gpt-image
Warn
Audited by Snyk on May 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts arbitrary HTTP/HTTPS image URLs and base64 data URIs as reference images in the required generation workflow (see SKILL.md / README.md "—image-url" support and scripts/generate.js which collects --image-url and includes image_urls in the API request to https://dragoncode.codes), so untrusted third‑party image content is ingested and can influence generation behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata