smart-ocr
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow is OCR of user-provided images/scanned PDFs (and potentially URL/bytes inputs), and the extracted OCR text is free-form content that can include outsider-authored text, which would be fed into the agent/LLM context as readable OCR output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata