gemini-prompting

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to ingest and analyze arbitrary user-supplied and web content — e.g., templates with [paste large document], multimodal inputs like [image]/video files and genai.upload_file(...), and a ReAct example using a search query — so the agent will read untrusted third-party content.