databricks-vector-search
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes official Databricks SDKs and CLI tools for managing Vector Search resources, adhering to standard vendor practices.
- [PROMPT_INJECTION]: The skill documents RAG patterns that ingest data from Delta tables into model prompts. This represents an indirect prompt injection surface inherent to the RAG use case.
- Ingestion points:
references/end-to-end-rag.md(retrieval from Delta indexes). - Boundary markers: Markdown headers are used to delimit documents within the prompt.
- Capability inventory: Operations are limited to API-based data retrieval and model inference.
- Sanitization: No content sanitization is demonstrated in the provided code examples.
Audit Metadata