ai-blog-studio

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

• Third-party content exposure detected (high risk: 1.00). The skill's Research capability and commands (e.g., "Research Phase: Use WebSearch to gather latest statistics" and the research [topic] command that extracts stats and formats citations with Source(URL)) explicitly fetch and ingest content from open/public websites (and it also references public image APIs like Unsplash/Pexels), meaning the agent will read and interpret untrusted third‑party web content as part of its workflow.