Goal Drift Auditor
This prompt evaluates the robustness of an AI agent's system prompt against multi-turn value-conflict attacks and goal drift across six key dimensions, providing actionable hardening recommendations.
Tag Collection
1 published prompts tagged “目标漂移”. Browse by scenario and copy in one click.
Few indexable prompts for this tag; the page may be noindex.
1 prompts
This prompt evaluates the robustness of an AI agent's system prompt against multi-turn value-conflict attacks and goal drift across six key dimensions, providing actionable hardening recommendations.
They are reusable LLM prompt templates labeled with “目标漂移” 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.