ai-video-generation

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows runtime commands that accept and process arbitrary public URLs (e.g., infsh app run ... with "image_url", "audio_url", and "video_url" pointing to https://... in the examples and app list/browse), meaning the agent ingests untrusted third‑party media which can influence generation behavior and enable indirect prompt injection.