tanstack-ai-persistence-server
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains legitimate documentation and code snippets for integrating
@tanstack/ai-persistence. It follows standard development patterns for middleware and state management.- [PROMPT_INJECTION]: The skill addresses potential indirect prompt injection by providing structured ways to reconstruct chat history and recommending the use of stable identifiers (threadId, runId). It emphasizes the use of an authorize callback in the reconstructChat utility to validate user access before processing requests.- [DATA_EXFILTRATION]: There are no patterns of unauthorized data exfiltration. The documented persistence mechanisms are designed for application-specific data storage and include explicit warnings against improper implementation that could lead to data exposure.
Audit Metadata