generate-image
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill can ingest untrusted third‑party content because its edit endpoint accepts arbitrary image_urls (e.g., the /edit call with example storage.googleapis.com images) and the listed enable_web_search option allows the model to fetch/use content from the open web via the fal.run API.
Audit Metadata