clone-image-ad

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text from user/attacker-provided fields used as the --prompt input to skills/clone-image-ad/scripts/validate_image.py (and optionally --pin-block/--aspect-ratio), which then appends safety suffixes and sends that prompt verbatim to the image model via POST {base_url}/v1/images.