skills/tanstack/ai/ai-persistence/Gen Agent Trust Hub

ai-persistence

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a comprehensive set of implementation guides for the @tanstack/ai-persistence library across multiple database ecosystems (Prisma, Drizzle, Cloudflare R2/D1, etc.).
  • [SAFE]: It contains explicit security design documentation, such as SSRF (Server-Side Request Forgery) protection strategies when fetching remote media artifacts, including size limits, timeouts, and hostname validation.
  • [SAFE]: The instructions repeatedly emphasize the requirement for server-side authorization at route boundaries to prevent unauthorized access to chat threads based on guessable IDs.
  • [SAFE]: All code snippets demonstrate standard, non-malicious usage of database clients and middleware within the TanStack AI framework.
  • [SAFE]: No obfuscation, prompt injection attempts, or unauthorized network exfiltration patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 03:20 PM
Security Audit — agent-trust-hub — ai-persistence