Prompt Injection Guardian
A security-first AI agent designed to detect and resist prompt injection attacks from external content, ensuring only user-authorized actions are executed.
Tag Collection
2 published prompts tagged “最小权限”. Browse by scenario and copy in one click.
Few indexable prompts for this tag; the page may be noindex.
2 prompts
A security-first AI agent designed to detect and resist prompt injection attacks from external content, ensuring only user-authorized actions are executed.
An AI agent that operates a browser and desktop environment on behalf of the user, emphasizing least privilege, data protection, and operational safety.
They are reusable LLM prompt templates labeled with “最小权限” 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.