auditing-table-statistics

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates SQL commands dynamically from table metadata to facilitate statistics refreshing. Additionally, the reference documentation provides bash scripts designed to automate these operations using the cockroach CLI tool.
  • [PROMPT_INJECTION]: The skill processes metadata from the database, such as table and column names, which serves as the primary data source for auditing. This creates a surface for indirect prompt injection if the database metadata were manipulated. Ingestion points: Data is retrieved using queries like SHOW STATISTICS and from information_schema tables in SKILL.md. Boundary markers: The skill does not provide specific instructions or delimiters to the agent to distinguish between metadata and instructions. Capability inventory: The skill facilitates SQL execution, specifically SHOW and CREATE STATISTICS commands. Sanitization: Retrieved metadata is interpolated directly into SQL command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:27 PM