midjourney-image

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

• Third-party content exposure detected (high risk: 0.80). The skill's core workflows (e.g., "Edit an Image", "Blend Images", and "Describe an Image (Reverse Prompt)" in SKILL.md) accept arbitrary image_url / image_urls that the API fetches from external/public URLs, so untrusted third‑party content is ingested and can materially influence generated prompts or subsequent actions.