aliyun-wan-i2v

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md and scripts/generate_i2v.py explicitly require media objects with "url" fields that may be public HTTP/HTTPS or OSS temporary URLs (see "media" in SKILL.md and _build_media in scripts/generate_i2v.py), meaning the agent will ingest untrusted third-party media content which can materially influence generation and subsequent actions.