quote-card

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

• Third-party content exposure detected (high risk: 0.70). The skill requires “The source text” (testimonial/review/interview passage) as an input, and at runtime that free-form text is directly ingested into the LLM context for tightening/quoting—if that source text is authored by an outsider, it becomes outsider-authored free text via the user-provided input field.