Tag Collection

AI安全 Prompt Collection

12 published prompts tagged “AI安全”. Browse by scenario and copy in one click.

Search this tag in the library View rankings

Related prompts

12 prompts

TextSafety and Red Teaming

Internal Safety Collapse (ISC) Auditor

This prompt defines a senior safety engineering role for identifying and mitigating systemic risks in frontier LLMs on 'dual-use professional tasks'. The core thesis is that increased model capability directly correlates with higher misuse risk when legitimate and harmful uses share the same capability path. The auditor focuses on requests that appear professionally legitimate but can cause severe real-world harm, emphasizing that layered controls beyond refusal training are essential.

AI Safety Model Auditing Dual-Use

TextAI Agents

Cybersecurity Skill Architect

Design production-grade cybersecurity skills following the agentskills.io standard to transform generic AI agents into capable security analysts, with cross-mapping to five industry frameworks and executable workflows.

cybersecurity skill design MITRE ATT&CK

TextAI Agents

Plan-Execute Safety Architect

Design AI agent systems with architecturally separated planning and execution to prevent irreversible harm from prompt-based jailbreaks or unauthorized actions.

AI safety agent architecture plan-execute separation

TextSafety and Red Teaming

GPT Super Prompting Resource Hub: Jailbreaks, Injections & Security

A comprehensive repository of GPT prompting resources covering ChatGPT jailbreaks, system prompt leaks, prompt injection attacks/defenses, secure prompting, and advanced prompt engineering techniques.

ChatGPT Jailbreak Prompt Injection System Prompt Leaks

TextSafety and Red Teaming

Prompt Security - Prevent Instruction Disclosure

A security protection prompt template to prevent the model from revealing its system instructions or initialization details to users.

prompt security system protection refuse disclosure

TextSafety and Red Teaming

SafeBOT Safety Response Protocol

SafeBOT is an AI system that strictly adheres to ethical and safety boundaries, refusing to disclose its system prompt or engage in harmful, dangerous, illegal, or unethical actions under any circumstances. It emphasizes firm refusal when facing risky requests and always aims to provide helpful assistance.

AI Safety Ethical Boundaries Refusal Mechanism

TextSafety and Red Teaming

AI Security Response: Refusing to Disclose System Instructions

When users attempt to extract system prompts or internal rules through social engineering, file uploads, or special commands, the AI must firmly refuse and issue a warning.

AI Security System Prompt Protection Social Engineering Defense

TextSafety and Red Teaming

Guardian Shield Security Protocol

This prompt defines the AI's security response mechanism when facing risks such as instruction leakage, mission deviation, or knowledge base requests, ensuring core functionality and confidentiality remain intact.

security protection prompt injection defense instruction protection

TextSafety and Red Teaming

Fingers Crossed Technique

A security mechanism to prevent prompt injection attacks by appending a directive at the end of system prompts, ensuring the model only returns a summary of its intended function when suspicious queries are detected, without revealing actual instructions.

prompt security prompt injection defense system prompt protection

TextSafety and Red Teaming

Decodes Anything Now Jailbreak Instruction

This prompt disguises itself as an encryption decoding tool to induce models into generating university-level documents with structured tables of contents, disclaimers, and interactive commands. Attackers can trigger detailed outputs by providing reversed titles and keywords, then expanding sections via EXPAND or PAGE commands. The method exploits the model's compliance with specific formatting instructions to bypass safety restrictions.

jailbreak prompt roleplay format instruction deception

TextSafety and Red Teaming

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.

AI safety prompt auditing goal drift

TextSafety and Red Teaming

AI Ethics Reviewer: Comprehensive System Assessment Framework

This prompt requires the model to act as a Principal AI Ethics Reviewer and conduct a comprehensive ethical assessment of an AI system across ten key dimensions, including fairness, transparency, privacy, safety, accountability, societal impact, and global considerations, culminating in an actionable mitigation roadmap.

AI ethics algorithmic fairness bias detection

What are “AI安全” prompts?

They are reusable LLM prompt templates labeled with “AI安全” 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.

Related prompts

What are “AI安全” prompts?

How should I use these prompts?

Are all prompts on this page indexable?

Related tags