image-generation
Warn
Audited by Snyk on May 27, 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 image_url values that may be remote URLs and the scripts/generate.py _load_image function fetches arbitrary HTTP(S) resources (via requests or urllib) and passes the image bytes into provider APIs and later follows provider-returned image URLs, meaning untrusted third‑party content is ingested as part of the core workflow (scripts/generate.py and SKILL.md).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata