aliyun-happyhorse-videoedit

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts arbitrary public HTTP/HTTPS URLs for the input video and reference images (see SKILL.md "input.media" url fields and the scripts/edit_happyhorse.py --video / --reference-image arguments), which are untrusted third‑party assets the service ingests and uses to determine editing behavior and therefore can materially influence actions.