llm-ops
Warn
Audited by Snyk on Sep 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). The RAG pipeline retrieves documents from a vector database (Chroma/pgvector) which can contain arbitrary external or user-submitted content ingested into the system.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata