ai-content-generation

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

• Third-party content exposure detected (medium risk: 0.30). In the project coach workflow, outsider-authored free text is ingested at runtime when the user pastes “real comments, DMs, and reviews” (audience words) into the “AI Ad Creative” prompts, and those prompts are then fed back to the LLM for hook/script generation.