ai-service-layer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The instructions specify installing the @domoinc/toolkit library, which is a package for a well-known business intelligence service.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle and parse output generated by AI models, which can be influenced by untrusted input data.
- Ingestion points: Untrusted data enters the context through AIClient.generate_text and AIClient.text_to_sql responses in SKILL.md.
- Boundary markers: The skill shows usage of prompt templates but does not demonstrate explicit boundary delimiters to isolate user input.
- Capability inventory: The skill facilitates the generation of SQL statements intended for execution against database schemas.
- Sanitization: The skill recommends defensive parsing patterns, including type validation and string trimming, to verify the structure of AI output before further processing.
Audit Metadata