image-editing

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts and fetches arbitrary public image URLs (see the "image_url" fields and the batch IMAGES list in SKILL.md) and uses those untrusted, third-party images as reference/target content that the agent must read and act on, which can materially influence editing decisions.