anti-ai-slop-writing

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow is a prose pre-processor that rewrites the user-provided text (“Applies to any prose before it ships”) without any trusted-source restriction, so outsider-authored free text that a caller submits to be processed is ingested by the LLM at runtime.