tanstack-ai-persistence-server

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). SKILL.md shows the server POST path only ingests client-provided chat request fields via chatParamsFromRequest(request) and uses them for chat state persistence, but the middleware itself is not shown to read any additional outsider-authored free text from external sources without first selecting client-provided messages.