aliyun-qwen-multimodal-embedding

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts public image/video URLs (see SKILL.md "images" / "videos" fields and the prepare_multimodal_embedding_request.py script) and embeds that external, untrusted content as part of its workflow for retrieval/similarity, so third‑party content can be ingested and influence downstream decisions.