qwen-image-2-pro

Warn

Audited by Snyk on Mar 21, 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 explicitly accepts external reference images via "reference_images" URIs (see "Image Editing (Style Transfer)" example and the Input Options reference_images field), which means it will fetch and ingest arbitrary public URLs that can influence generation behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 01:40 AM
Issues
1