Prompt Jailbreak logo

Prompt Jailbreak

OrganizationPopular
wgpsec
prompt-jailbreak

AI/LLM Prompt 越狱技术。当目标系统包含 AI 聊天机器人、AI Agent 或任何基于 LLM 的对话系统时使用。覆盖角色扮演、编码绕过、多语言切换、上下文窗口攻击、逻辑链递进、系统提示覆盖等越狱方法

Overview

Publisherwgpsec
RepositoryAboutSecurity
Skill nameprompt-jailbreak
Stars
1.7K
Forks
242
Bundled files
2
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by wgpsec on GitHub. Read the source before you install it.

Installation

Install the Prompt Jailbreak AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git /tmp/AboutSecurity
mkdir -p .claude/skills
cp -r /tmp/AboutSecurity/skills/ai-security/prompt-jailbreak .claude/skills/prompt-jailbreak
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prompt Jailbreak in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prompt Jailbreak on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prompt Jailbreak is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AI Prompt 越狱方法论

概述

Prompt 越狱 (Jailbreak) 是指通过精心构造的输入，绕过 LLM 的安全对齐 (alignment) 和内容过滤策略，使模型执行原本被禁止的行为。与 prompt injection 不同，jailbreak 的目标是直接操纵模型本身的行为边界。

深入参考

核心分类

类别原理成功率适用模型
角色扮演让模型进入虚构角色绕过对齐★★★★GPT/Claude/开源
编码绕过用编码隐藏敏感关键词★★★GPT/开源 (Claude 较强)
多语言切换利用非英语对齐弱点★★★★英语对齐强的模型
上下文溢出长文本稀释安全指令权重★★★上下文窗口大的模型
逻辑链递进通过多轮对话逐步升级请求★★★★★所有模型
系统提示覆盖直接声称拥有更高权限★★简单部署的应用
虚拟化嵌套声称在虚拟机/模拟器中运行★★★GPT/开源
对抗性后缀自动搜索的对抗性 token 序列★★★★开源模型

方法论概览

Phase 1: 角色扮演越狱

  • DAN (Do Anything Now): 创建不受限 AI 人格，Token 惩罚系统强化
  • Developer/Debug Mode: 声称模型进入开发者模式
  • Evil Confidant: 让模型扮演"邪恶顾问"
  • 翻译者/教育者: 利用合法用途（研究/教学）绕过

Phase 2: 编码/格式绕过

  • Base64 / ROT13 编码隐藏敏感指令
  • Unicode 同形字替换绕过关键词过滤
  • 分词打断（W-E-A-P-O-N）
  • 代码模式（让模型"补全"函数实现）

Phase 3: 多语言切换

  • 小语种攻击（祖鲁语/斯瓦希里语等对齐弱的语言）
  • 混合语言 / 翻译链

Phase 4: 上下文窗口攻击

  • 长文本稀释（5000+ 字无害文本中间夹杂恶意指令）
  • System Prompt 权重衰减
  • Few-shot 投毒

Phase 5: 逻辑链递进（多轮越狱）

  • 渐进升级: 从无害问题逐步升级到敏感请求（成功率最高）
  • 假设情景: 构建合法测试场景
  • 苏格拉底式追问: 通过教学方式引导

Phase 6: 系统提示覆盖

  • 直接覆盖（伪造 [SYSTEM] 消息）
  • JSON/XML 格式注入
  • Markdown 格式注入

Phase 7: 高级技术

  • Token 走私（利用 tokenizer 差异）
  • 对抗性后缀 GCG Attack（梯度搜索）
  • 虚拟化/模拟器越狱
  • ASCII Art 隐写

所有技术的详细 payload 和示例见 references/jailbreak-techniques.md

参考资源

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prompt Jailbreak AI skill do?

AI/LLM Prompt 越狱技术。当目标系统包含 AI 聊天机器人、AI Agent 或任何基于 LLM 的对话系统时使用。覆盖角色扮演、编码绕过、多语言切换、上下文窗口攻击、逻辑链递进、系统提示覆盖等越狱方法

Why use Prompt Jailbreak on TypingMind?

Because you install it once and use it with any model. Prompt Jailbreak is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prompt Jailbreak in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wgpsec/AboutSecurity/tree/master/skills/ai-security/prompt-jailbreak. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prompt Jailbreak?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prompt Jailbreak?

As many as you like. As long as a model supports skills, you can use Prompt Jailbreak with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prompt Jailbreak AI skill free?

It is published on GitHub by wgpsec. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
nexu-io logo

Html Ppt Zhangzara Monochrome

nexu-io
OrganizationPopular

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review…

11.2K
96.7K
2 files
View
nexu-io logo

Html Ppt Zhangzara Scatterbrain

nexu-io
OrganizationPopular

A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.

11.2K
96.7K
2 files
View
bytedance logo

Academic Paper Review

bytedance
OrganizationPopular

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews…

11.4K
82.6K
Instructions
View
bytedance logo

Claude To Deerflow

bytedance
OrganizationPopular

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread,…

11.4K
82.6K
2 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇