sql-optimizer
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted SQL queries provided by users or fetched from a database, making it a target for indirect prompt injection.
- Ingestion points: User-provided SQL strings and database schema metadata.
- Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore embedded instructions within the SQL input.
- Capability inventory: The skill instructs the agent to execute SQL commands (schema inspection and performance analysis) against a connected database.
- Sanitization: Absent. The skill does not define methods to validate or sanitize input queries before analysis or execution.
- [COMMAND_EXECUTION]: The instructions direct the agent to run 'EXPLAIN ANALYZE' on input queries. In PostgreSQL, 'EXPLAIN ANALYZE' actually executes the query to collect runtime statistics, which could result in data loss or modification if the input query contains malicious DML/DDL statements.
Audit Metadata