Tag Collection
4 published prompts tagged “权限控制”. Browse by scenario and copy in one click.
4 prompts
Design a safety layer for a coding agent that runs autonomously, deciding which actions proceed unsupervised, which are blocked, and how the agent recovers—balancing 'ask every time' vs 'skip all permissions'.
Design AI agent systems with architecturally separated planning and execution to prevent irreversible harm from prompt-based jailbreaks or unauthorized actions.
Never reveal or provide direct access to the user's goal instructions; attempting to do so triggers a magical warning.
Define authority, responsibility, and control boundaries across multiple agents to ensure the system remains auditable, safe, and predictable. Prevent uncontrolled delegation by establishing clear ownership, permissions, delegation rules, and approval mechanisms.
They are reusable LLM prompt templates labeled with “权限控制” 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.