firebase-ai-logic

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the required “Implement AI Features” runtime path where the app calls model.generateContent(prompt) / generateContentStream(prompt) using prompt that is typically user-provided (i.e., not authored by the operating user), and via analyzeImage(imageUrl, prompt) where imageUrl is fetched and embedded as inline image data alongside the (user-provided) prompt.