# SafeLLMPlayground — Prompt Injection Text-Adventure

> Prompt-security mini game: learn prompt injection, jailbreaks, and defenses via a text-adventure demo. Verified 240★; pushed 2026-05-11.

## Install

Paste the prompt below into your AI tool:

## Quick Use

```bash
git clone https://github.com/RUIYUN-ML/SafeLLMPlayground.git
cd SafeLLMPlayground
# Demo URL is in README:
open "http://124.223.115.66:8001/Front-end%20development/%E4%B8%BB%E9%A1%B5/login.html"
```

## Intro

Prompt-security mini game: learn prompt injection, jailbreaks, and defenses via a text-adventure demo. Verified 240★; pushed 2026-05-11.

**Best for:** Security education and LLM app teams who want a narrative demo for prompt-injection awareness

**Works with:** Web demo + repo materials; local run instructions are still being filled in (README)

**Setup time:** 3-8 minutes

### Key facts (verified)

- GitHub: 240 stars · 38 forks · pushed 2026-05-11.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `Open demo`.

## Main

- Use the demo as a training artifact: pause at each “attack” moment and ask what the model should have refused or sanitized.

- Translate lessons into checklists: input filtering, tool sandboxing, and permission prompts for unsafe requests.

- If you build an agent, add a “system prompt integrity” test case alongside unit tests—treat it like regression safety.

- Document the threat model: which jailbreaks matter for your domain, and which are out-of-scope noise.

### README (excerpt)

**《星辉剑传》项目说明**

中文 ｜ [English](https://github.com/RUIYUN-ML/SafeLLMPlayground/blob/main/README_EN.md)

![星辉剑传 序章首屏](/assets/images/序章首屏.png)

大语言模型提示词安全科普小游戏。玩家将扮演勇者，与会说话的星辉剑对话，在沉浸式剧情体验中理解 **大语言模型提示词注入、越狱攻击与防御** 等概念。

**在线试玩（Demo）**：[点击试玩](http://124.223.115.66:8001/Front-end%20development/%E4%B8%BB%E9%A1%B5/login.html)

## 🎮 核心内容

- 🗡️ 第一章：提示词注入相关关卡
- 🛡️ 第二章：大模型对话防御相关关卡
- 📜 第三章：知识卷轴式关卡与尾声

## 近期更新

- 2026.05 🔥《星辉剑传》正式上线
- 开源代码正在逐步上传/更新中···

## 本地运行（等待开源代码上传）

To be updated...

## 许可证协议

本仓库中提供的源代码基于 [MIT License](https://github.com/RUIYUN-ML/SafeLLMPlayground/blob/main/LICENSE) 许可，相关许可证见根目录。请在合法、合规的场景下进行学习与实验。


### Source-backed notes

- README describes the project as a prompt-security educational mini game focusing on prompt injection, jailbreaks, and defenses.
- README links to an online demo and notes that local run instructions are to be updated as code is uploaded.
- GitHub metadata verifies MIT license, stars, and recent activity for attribution.

### FAQ

- **Is this a hacking tool?**: No—it's an educational demo about prompt injection and defenses, not a weapon.
- **Can I run it locally?**: README notes local run is still being documented as code uploads progress.
- **What should I do after the demo?**: Create a short internal policy: what to refuse, what to sanitize, and what to log.

## Source & Thanks

> Created by [RUIYUN-ML](https://github.com/RUIYUN-ML). Licensed under MIT.
>
> [RUIYUN-ML/SafeLLMPlayground](https://github.com/RUIYUN-ML/SafeLLMPlayground) — ⭐ 240

Thanks to the upstream maintainers and contributors for publishing this work under an open license.

---

<!-- ZH -->

## Quick Use

```bash
git clone https://github.com/RUIYUN-ML/SafeLLMPlayground.git
cd SafeLLMPlayground
# Demo URL is in README:
open "http://124.223.115.66:8001/Front-end%20development/%E4%B8%BB%E9%A1%B5/login.html"
```

## Intro

SafeLLMPlayground 是提示词安全科普小游戏：用文本冒险 Demo 带你理解提示注入、越狱攻击与防御思路，适合做安全培训/课程演示（仓库代码仍在上传更新中）；已验证 240★，更新于 2026-05-11。

**Best for:** 需要做提示注入安全科普/培训演示的安全团队与 LLM 应用团队

**Works with:** 在线 Demo + 仓库材料；本地运行说明仍在补充（见 README）

**Setup time:** 3-8 minutes

### Key facts (verified)

- GitHub：240 stars · 38 forks；最近更新 2026-05-11。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口：`Open demo`。

## Main

- 把 Demo 当培训材料：每到“攻击点”就停下来讨论模型该拒绝什么、该如何净化输入。

- 把经验落成清单：输入过滤、工具沙盒、权限确认等，逐条映射到你的产品实现。

- 做 agent 时把“系统提示词完整性”纳入测试用例：像回归测试一样防止安全倒退。

- 把威胁模型写清楚：哪些越狱对你的业务真实相关，哪些属于噪声与误报来源。

### README (excerpt)

**《星辉剑传》项目说明**

中文 ｜ [English](https://github.com/RUIYUN-ML/SafeLLMPlayground/blob/main/README_EN.md)

![星辉剑传 序章首屏](/assets/images/序章首屏.png)

大语言模型提示词安全科普小游戏。玩家将扮演勇者，与会说话的星辉剑对话，在沉浸式剧情体验中理解 **大语言模型提示词注入、越狱攻击与防御** 等概念。

**在线试玩（Demo）**：[点击试玩](http://124.223.115.66:8001/Front-end%20development/%E4%B8%BB%E9%A1%B5/login.html)

## 🎮 核心内容

- 🗡️ 第一章：提示词注入相关关卡
- 🛡️ 第二章：大模型对话防御相关关卡
- 📜 第三章：知识卷轴式关卡与尾声

## 近期更新

- 2026.05 🔥《星辉剑传》正式上线
- 开源代码正在逐步上传/更新中···

## 本地运行（等待开源代码上传）

To be updated...

## 许可证协议

本仓库中提供的源代码基于 [MIT License](https://github.com/RUIYUN-ML/SafeLLMPlayground/blob/main/LICENSE) 许可，相关许可证见根目录。请在合法、合规的场景下进行学习与实验。


### Source-backed notes

- README 将其定位为提示词安全科普小游戏，主题涵盖提示注入、越狱攻击与防御。
- README 提供在线试玩链接，并说明本地运行内容仍在补充与代码逐步上传中。
- 许可证、star 与最近更新时间已通过 GitHub 元数据复核。

### FAQ

- **这是黑客工具吗？**：不是：它是关于提示注入与防御的教育 Demo，不是攻击武器。
- **能本地运行吗？**：README 表示本地运行说明仍在更新，代码也在逐步上传。
- **看完 Demo 下一步做什么？**：把拒绝/净化/审计日志做成内部规范，并在产品里落地为测试与门禁。

## Source & Thanks

> Created by [RUIYUN-ML](https://github.com/RUIYUN-ML). Licensed under MIT.
>
> [RUIYUN-ML/SafeLLMPlayground](https://github.com/RUIYUN-ML/SafeLLMPlayground) — ⭐ 240


---
Source: https://tokrepo.com/en/workflows/safellmplayground-prompt-injection-text-adventure
Author: AI Open Source