reading-business-cards
Warn
Audited by Snyk on Jul 30, 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). The runtime workflow reads outsider-authored content by ingesting user-provided business-card images, tiling/cropping them in
prep_cards.py, and then sending the resulting image tiles to the LLM inextract_cards.pyvia theview/call_haikupath (base64-embedded PNGs).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata