Art

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

• Third-party content exposure detected (medium risk: 0.30). In Workflows/Essay.md, the required runtime reads the user/content input (including optional paste/URL via CSE-24) to extract narrative/thesis and then uses that extracted freeform text to construct the generation prompt—so outsider-authored text can flow into the LLM at runtime.