prisma-database-modelling
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No security issues detected. The skill is purely informational, providing best practices and examples for data modeling.
- [Indirect Prompt Injection] (LOW): The skill processes user-provided database requirements to generate Prisma schemas. This represents a standard input surface for an LLM-based tool with no associated high-risk capabilities like code execution or network access.
- Ingestion points: User instructions regarding database structure.
- Boundary markers: None explicitly defined for input, but output is restricted to Prisma snippets.
- Capability inventory: None. The skill generates text and code snippets only.
- Sanitization: Not applicable as no execution occurs.
Audit Metadata