databricks-synthetic-data-gen
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is data generation for testing and development, and its implementation uses standard, documented features of the Databricks platform without any hidden or suspicious logic.\n- [COMMAND_EXECUTION]: The skill provides instructions for necessary CLI operations, such as installing packages via
uvorpipand deploying scripts using thedatabricksCLI, which are consistent with its intended use case.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes well-known Python packages (faker,numpy,pandas,holidays,polars) from official PyPI registries to facilitate data generation.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it translates user requirements into Spark code, but it enforces robust controls to prevent unauthorized execution.\n - Ingestion points: User-provided data domains, table schemas, and row counts defined in the 'Generation Planning Workflow' section of
SKILL.md.\n - Boundary markers: The skill explicitly mandates a 'Plan for user approval' and a 'Pre-Generation Checklist' before any code is produced.\n
- Capability inventory: The agent is capable of executing
spark.sqlcommands and writing data to cloud storage volumes, as shown inscripts/generate_synthetic_data.py.\n - Sanitization: The skill relies on human-in-the-loop validation, requiring the user to confirm catalog and schema details before proceeding.
Audit Metadata