fal-video-edit

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts (scripts/edit-video.sh and scripts/video-audio.sh) require an arbitrary --video-url which is sent to remote model endpoints at https://queue.fal.run/$MODEL, so untrusted public video content will be ingested and interpreted by the models (allowing embedded/user-generated content to influence model behavior and potentially perform indirect prompt-injection).