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 uv or pip and deploying scripts using the databricks CLI, 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.sql commands and writing data to cloud storage volumes, as shown in scripts/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
Risk Level
SAFE
Analyzed
Aug 11, 2026, 02:51 PM
Security Audit — agent-trust-hub — databricks-synthetic-data-gen