databricks-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (specifically SQL injection) because it interpolates user-provided or external data into SQL commands.
- Ingestion points: Functions in
SKILL.mdsuch asoptimize_delta_table,enable_liquid_clustering, andenable_predictive_optimizationtake arguments liketable_name,z_order_columns, andcluster_columnswhich are directly embedded into SQL strings. - Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the prompt templates.
- Capability inventory: The skill uses
spark.sql()inSKILL.mdto execute administrative and maintenance tasks on the Databricks cluster. - Sanitization: The code uses Python f-strings (e.g.,
spark.sql(f"OPTIMIZE {table_name}")) to build queries, lacking escaping or validation for the identifiers being passed.
Audit Metadata