domo-sql-client
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow where user-supplied natural language is processed by an AI to generate SQL queries which are subsequently executed. This configuration is susceptible to indirect prompt injection.
- Ingestion points: Natural language input is accepted by the AIClient.text_to_sql method as shown in SKILL.md.
- Boundary markers: The provided implementation lacks clear delimiters or instructions to ignore malicious directives embedded within the natural language input.
- Capability inventory: The sqlClient.get method in SKILL.md provides the capability to execute the resulting SQL against database aliases.
- Sanitization: There is no evidence of sanitization or structural validation performed on the AI-generated SQL before it is executed.
Audit Metadata