fal-video

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly consumes and acts on untrusted third-party API responses from fal.ai: scripts/fal_queue_video_run.py (using _fal_common.queue_get_by_url and collect_media_outputs) walks the result payload (e.g., video.url), follows response/status URLs, and downloads arbitrary media URLs returned by the platform, so remote payloads directly control polling, downloads, and subsequent tool actions.