design-theme-guide
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user input, such as business names and design specifications, and directly interpolates these into generated artifacts like SQL DDL and CSV files.\n
- Ingestion points: Data provided by the user in Step 2 regarding Identity, Surface, Type, Access, and Governance.\n
- Boundary markers: The instructions suggest keeping prose separate from data but do not define specific delimiters or guardrails for the interpolation of user values into code blocks.\n
- Capability inventory: The skill's primary capability is text generation of data registries in common formats (SQL, JSON, CSV).\n
- Sanitization: There are no instructions for sanitizing, validating, or escaping user input before it is placed into the output templates.\n- [EXTERNAL_DOWNLOADS]: The skill references an official JSON schema at https://json-schema.org/draft/2020-12/schema for its JSON output. This reference targets a well-known technical service and is documented neutrally as a standard part of the data generation process.
Audit Metadata