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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:52 PM