magazine-explainer

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

• Third-party content exposure detected (medium risk: 0.30). The outsider-written text (the user’s topic/kid details and any existing chat/article context) is consumed by the required workflow’s LLM drafting + auditing steps (“Research”, “Draft the narrative”, and the REQUIRED “Audit the prose … stop-slop skill”), which then gets rendered into the output PDF.