databricks-agent-bricks
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM via the Knowledge Assistant’s RAG over user-specified Volume files (PDF/TXT/MD/DOCX) and/or Vector Search index documents, where the ingested document body is not authored by the operating user and is read at runtime for retrieval.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata