jina-ai
Warn
Audited by Snyk on Aug 10, 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). Jina’s required runtime workflow includes
scripts/dedup_images.py, which reads attacker-supplied stdin lines or URL/path arguments and sends them to Jina’s embeddings API (API_URLhttps://api.jina.ai/v1/embeddings) for processing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata