databricks-agent-bricks

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's content and instructions align with the intended administrative use cases for the Databricks platform and contain no malicious intent or security bypasses.
  • [COMMAND_EXECUTION]: The skill uses the official databricks CLI to interact with workspace resources. These commands are executed within the user's authenticated session and do not involve unsanitized input or arbitrary execution.
  • [CREDENTIALS_UNSAFE]: The documentation for creating external connections uses generic placeholders (e.g., <sp_id>, <sp_secret>) for authentication details. No actual credentials or sensitive keys are hardcoded.
  • [DATA_EXFILTRATION]: Instructions facilitate agent access to data in Unity Catalog Volumes. All data access is governed by the platform's internal permission system, and no unauthorized exfiltration paths were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:24 PM
Security Audit — agent-trust-hub — databricks-agent-bricks