databricks-performance-tuning

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Multiple functions in SKILL.md, including optimize_delta_table, enable_liquid_clustering, and enable_predictive_optimization, use f-string interpolation to build SQL commands. This creates a risk of SQL injection where a malicious table name could be used to execute arbitrary SQL statements on the Spark cluster.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external data (table and column names) and interpolates it into executable code without sanitization.\n
  • Ingestion points: Function parameters table_name, z_order_columns, and cluster_columns within SKILL.md.\n
  • Boundary markers: Absent; there are no delimiters or warnings to the agent to ignore instructions embedded within the data.\n
  • Capability inventory: Uses spark.sql() to execute commands on the data platform (identified in SKILL.md).\n
  • Sanitization: Absent; input is directly concatenated into SQL strings without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:25 AM