video-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and fetches arbitrary public image URLs via the top-level "image_urls" parameter (see the Image-to-Video examples in SKILL.md), meaning the agent ingests untrusted third-party content that it must interpret to decide how to generate videos and thus could be influenced by embedded or user-generated instructions.