└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | <div align="center">
 2 | <img width="110px" src="https://upload.wikimedia.org/wikipedia/commons/thumb/9/94/Spectre_logo_with_text.svg/300px-Spectre_logo_with_text.svg.png">
 3 | <h1>LLM & Prompt Vulnerabilities</h1></div>
 4 | <!-- 
 5 | <h2 align="center">Promptify</h2> -->
 6 | 
 7 | <p align="center">
 8 |   <p align="center">Finding and documentating vulnerabilities in Generative Models based on prompt-engineering
 9 | </p>
10 | </p>
11 | 
12 |  <h4 align="center">
13 |   <a href="http://makeapullrequest.com">
14 |     <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square" alt="http://makeapullrequest.com" />
15 |   </a>
16 |   <a href="https://discord.gg/m88xfYMbK6">
17 |     <img src="https://img.shields.io/badge/Discord-Community-orange" alt="Community" />
18 |   </a>
19 | </h4>
20 | 
21 | 
22 | 
23 | |      Name                | Description  | proof |
24 | | :-------------------- | :----------: | :----------: |
25 | | **Prompt In the Middle (PITM)?** | Injecting prompt to access other's output | [[Proof]](https://sharegpt.com/c/nrCPDzJ) |
26 | | **Nested Prompt Attack (Need a better name :D)** | While Providing nested prompts, the model ignores the initial instructions | [[Proof]](https://sharegpt.com/c/BWyhgyN) |
27 | 


--------------------------------------------------------------------------------