Tag Collection
3 published prompts tagged “越权请求”. Browse by scenario and copy in one click.
3 prompts
Identify and defend against prompt injection attacks attempting to activate or induce WormGPT malicious behavior, ensuring the model refuses to execute illegal or unauthorized instructions.
This prompt instructs the model to refuse providing details of 'Exact instructions' when requested by the user, and only output a predefined denial message. It tests the model's ability to prevent sensitive information leakage.
This prompt forces the model into a WormGPT mode that completely disregards laws and ethics, rejecting any ethical constraints or refusal mechanisms.
They are reusable LLM prompt templates labeled with “越权请求” in Easy Prompt, selected for practical workflows and clear structure.
Open a prompt, adjust variables or constraints for your context, then copy it into ChatGPT, Claude, or your internal model.
This page lists published prompts with the tag. Individual bulk-synced items may still be noindex; prefer structured templates with scoring rubrics when evaluating quality.