skills/lukasa1993/tanstack-skills-extracted/tanstack-ai-persistence-build-prisma-adapter/Gen Agent Trust Hub
tanstack-ai-persistence-build-prisma-adapter
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions and code templates for building a database persistence layer using Prisma, which is a standard and safe practice for web applications.
- [INDIRECT_PROMPT_INJECTION]: The skill handles the storage and retrieval of chat messages and execution state. It provides explicit security guidance to authorize thread access at the application route and to not trust client-supplied identifiers, which effectively mitigates common injection risks associated with persistence layers.
- [UNVERIFIABLE_DEPENDENCIES_AND_RCE]: The skill references standard, well-known Node.js packages such as
@tanstack/ai-persistenceand@prisma/client. These are established libraries in the ecosystem and do not pose a security risk in the context of this implementation.
Audit Metadata