image-analyzer
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The workflow explicitly fetches and OCRs images from user-supplied external URLs (e.g.,
v1/proxy/orthogonal/runwithapi: linkup/scrapegraphandbody.url), so outsider-authored free text from arbitrary websites/images can be ingested into the agent’s LLM context via the OCR/scraping outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata