query-writing
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- Data Ingestion Surface: The skill is designed to interact with external databases, which is a common pattern for data analysis tools. Ingestion points: Data enters the agent context through the sql_db_schema and sql_db_query tools referenced in SKILL.md. Boundary markers: The instructions do not include specific delimiters to separate database content from agent instructions. Capability inventory: The skill is equipped to inspect database structures and perform read-only queries. Sanitization: There are no explicit sanitization steps defined within the skill's markdown instructions.
- Data Integrity Protections: The guidelines explicitly prohibit the use of Data Manipulation Language (DML) commands such as INSERT, UPDATE, DELETE, and DROP. This measure helps ensure that the agent's actions are restricted to data retrieval and analysis, minimizing the risk of accidental data loss or modification.
Audit Metadata