ft-evaluate-christian-ai-apps

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

• Third-party content exposure detected (high risk: 1.00). The Quick Start and references/test-questions.md explicitly require opening an external AI app's chat interface and recording/ scoring that app's exact responses (i.e., ingesting untrusted third‑party chat outputs), which the workflow uses to determine pass/ fail and subsequent actions.