Virtual Try-On

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly requires supplying image_urls (e.g., Quick Start and "Using image_urls" examples) which the each::sense API will fetch and process from arbitrary public URLs, meaning untrusted third‑party content is ingested and can directly influence model/tool behavior.