lov-image-translation-errata
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Required workflow Step 0–Step 2 ingests and transcribes free text that appears inside the user-supplied screenshot (Step 0.4 explicitly treats “instruction printed inside an image” as quoted content), then uses it to build the translation evidence map.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata