eachlabs-video-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts arbitrary public URLs (e.g., image_url, video_url, audio_url) in the POST to https://api.eachlabs.ai/v1/prediction so the system will ingest and process untrusted third-party content from the open web, enabling indirect prompt injection via that media.