Home/Wiki Errors/AI Video
AI Video / Prompt safety

AI video safety rejection in Veo / Sora / Kling

The video model rejected the prompt because it looked unsafe, copyrighted, celebrity-like, or policy-sensitive.

Error text / 报错原文

  • safety rejection
  • prompt violates policy
  • unable to generate video

What it means

The video model rejected the prompt because it looked unsafe, copyrighted, celebrity-like, or policy-sensitive.

Most common causes

  • Named celebrity or brand
  • Violence or medical claims
  • Copyrighted character
  • Ambiguous unsafe action

Fastest fix

  • Reproduce the smallest failing case.
  • Check environment, platform, and production settings.
  • Use the related local tool to classify the issue.
  • Fix the highest-risk security or data issue first.

Safe fix

  • Keep secrets out of client code and logs.
  • Prefer least privilege and explicit allowlists.
  • Add a regression test or checklist before retrying.
  • Document the working production configuration.

What not to do

  • Do not disable security controls as a permanent fix.
  • Do not paste secrets into public issue trackers or AI chats.
  • Do not trust preview success as production readiness.

Diagnostic commands

nvidia-smi
python -c "import torch; print(torch.cuda.is_available())"
python --version

Related tools

Related errors

Sources