databricks-ml-training
Warn
Audited by Snyk on Sep 25, 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 custom GenAI agent skill builds a LangGraph assistant with Vector Search retrieval and UC function tools that query ingested tables and documents, exposing the benign agent to outsider-authored free text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata