---
id: 7807
title: "Exploiting a Generative AI Chatbot – Prompt Injection to Remote Code Execution (RCE)"
source_domain: netspi.com
source_url: "https://www.netspi.com/blog/technical-blog/ai-ml-pentesting/how-to-exploit-a-generative-ai-chatbot-using-prompt-injection/"
published_at: "2024-07-16T00:00:00Z"
tags: ["ai-security", "rce", "prompt-injection", "llm-security", "ai-pentesting", "chatbot"]
phying_url: "https://phying.com/item/7807"
lang: en
---

# Exploiting a Generative AI Chatbot – Prompt Injection to Remote Code Execution (RCE)

## Summary

NetSPI built a deliberately vulnerable LLM chatbot to demonstrate prompt injection risks. The walkthrough shows how injected prompts enable data disclosure and, with code execution features, RCE.

## Intelligence Metadata

- **Sources:** netspi.com
- **Published:** 2024-07-16T00:00:00Z
- **Original:** https://www.netspi.com/blog/technical-blog/ai-ml-pentesting/how-to-exploit-a-generative-ai-chatbot-using-prompt-injection/
- **Phying News:** https://phying.com/item/7807