databricks-agent-bricks
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official
databricksCLI (version >= 1.0.0 or >= 0.299.2 for beta features) to manage AI resources within a Databricks workspace. All commands are standard administrative operations for creating Knowledge Assistants, syncing sources, and orchestrating agents. - [CREDENTIALS_UNSAFE]: References to sensitive fields such as
client_secretorsp_secretin SQL examples for Unity Catalog connections use safe placeholder syntax (e.g.,<sp_secret>) rather than hardcoding actual credentials. - [EXTERNAL_DOWNLOADS]: The skill references standard Databricks service endpoints and official documentation patterns. No unauthorized or untrusted external downloads are initiated.
- [SAFE]: The skill is a legitimate technical guide for Databricks-specific AI functionality. While it involves processing untrusted data (documents in Volumes for RAG), this is the intended primary purpose of the 'Knowledge Assistant' feature and is handled by the platform's infrastructure.
Audit Metadata