image-to-video

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

• Third-party content exposure detected (high risk: 0.80). The skill's Quick Start and many examples in SKILL.md require submitting arbitrary publicly accessible image_urls (and the error handling explicitly says "Use publicly accessible image URLs"), so the agent fetches and interprets untrusted third-party images as part of its workflow which can materially influence its generated outputs.