eachlabs-image-edit

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts and processes arbitrary public image URLs (see the "image_url"/"image_urls" fields in the prediction POST examples such as edit, remove background, upscale, and virtual try-on), meaning the agent will fetch and interpret untrusted third-party content from the open web and could be exposed to indirect prompt injection.