generate-sql
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by processing natural language user requirements into executable SQL queries for internal tools.
- Ingestion points: User-provided query requirements and behavior descriptions (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions embedded in user-supplied data during the SQL generation process.
- Capability inventory: The skill has the capability to execute queries via 'ae-cli analysis adhoc run' and retrieve metadata via 'ae-cli analysis-meta' (SKILL.md).
- Sanitization: There is no mention of sanitizing or validating user input to prevent the generation of unauthorized or harmful SQL statements before tool invocation.
Audit Metadata