databricks-lakebase-autoscale

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The connection-patterns.md file contains a utility function resolve_hostname that executes the dig command using subprocess.run. While it uses a list of arguments to mitigate shell injection, it invokes an external system binary with input derived from resource properties.
  • [PROMPT_INJECTION]: The skill facilitates data ingestion from external Unity Catalog tables into a PostgreSQL database via Reverse ETL, creating an indirect prompt injection surface.
  • Ingestion points: Data is pulled from source tables specified by the source_table_full_name parameter in reverse-etl.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are implemented in the synchronization logic.
  • Capability inventory: The skill possesses extensive capabilities, including creating/deleting infrastructure via databricks-sdk, generating authentication tokens, and executing SQL queries via psycopg.
  • Sanitization: No explicit sanitization or validation of the synced data content is demonstrated before it reaches the operational database.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 07:54 PM