alibabacloud-avatar-video

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

• Third-party content exposure detected (high risk: 0.90). The skill's LingMou workflow explicitly calls list_public_broadcast_scene_templates and copy_broadcast_scene_from_template (see scripts/avatar_video.py and SKILL.md / references/lingmou-api.md) to fetch public broadcast templates and then inspects their template details/variables and uses them to create videos, so untrusted third‑party template content is ingested and can directly influence which template/variables (and thus generation behavior) the agent uses.