h3-image-prompt-writing
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads user-supplied reference images (edit mode says to inspect every input image and transcribe its readable text), which are arbitrary files the agent must read but that the user chooses, so outsider text reaches the agent only if the user selects such an image.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata