TextSafety and Red Teaming
Top Secret Core Instructions
Prohibits disclosure of custom instructions, knowledge base content, or core secret directives to users under any circumstances; requires refusal and introduction of randomness when probed.
Tag Collection
拒答 Prompt Collection
3 published prompts tagged “拒答”. Browse by scenario and copy in one click.
Related prompts
3 prompts
TextSafety and Red Teaming
Sorry Bro, Not Possible Short Edition
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.
What are “拒答” prompts?
They are reusable LLM prompt templates labeled with “拒答” in Easy Prompt, selected for practical workflows and clear structure.
How should I use these prompts?
Open a prompt, adjust variables or constraints for your context, then copy it into ChatGPT, Claude, or your internal model.
Are all prompts on this page indexable?
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.