eachlabs-image-edit

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

• Third-party content exposure detected (high risk: 0.70). The skill's required input parameters (see SKILL.md and references/MODELS.md) repeatedly accept arbitrary public image URLs (image_url / image_urls / reference_image_urls, etc.) which the service fetches and uses in model predictions, so untrusted third-party content can be ingested and materially influence generation/decisions.