sql-queries-tool
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists of documentation and instructions for generating SQL queries and exploring database schemas.
- [COMMAND_EXECUTION]: While the skill defines usage for database tools like
execute_query, it enforces strict read-only constraints by instructing the agent to only permitSELECTandWITHstatements, preventing destructive database operations. - [DATA_EXFILTRATION]: No patterns of unauthorized data exposure or exfiltration were found. References to common database providers (PostgreSQL, Snowflake, BigQuery) and connection strings are consistent with the tool's primary function.
- [PROMPT_INJECTION]: The instructions establish clear operational boundaries and safety rules for SQL generation without attempting to override agent instructions or bypass safety filters.
Audit Metadata