alicloud-ai-research-qwen-deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly states it is for "run iterative web research" and produce reports with citations (SKILL.md description) and accepts external "attachments" (image URLs) in the normalized interface, indicating the agent will ingest open/public third‑party content (web pages/images) that could influence its actions.