Exploiting Vulnerabilities in LLM APIs

👩‍🎓👨‍🎓 Learn about Large Language Model (LLM) attacks! This lab contains an OS command injection vulnerability that can be exploited via its APIs. We can call these APIs via the LLM. To solve the lab, we must delete the morale.txt file from Carlos' home directory.

If you're struggling with the concepts covered in this lab, please review https://portswigger.net/web-security/... 🧠

🔗 Portswigger challenge: https://portswigger.net/web-security/...

🧑💻 Sign up and start hacking right now - https://go.intigriti.com/register

👾 Join our Discord - https://go.intigriti.com/discord

🎙️ This show is hosted by   / _cryptocat   ( ‪@_CryptoCat‬ ) &   / intigriti  

👕 Do you want some Intigriti Swag? Check out https://swag.intigriti.com

Overview:
0:00 Intro
0:29 Chaining vulnerabilities in LLM APIs
0:50 Lab: Exploiting vulnerabilities in LLM APIs
1:32 Probe LLM chatbot
4:09 Find OS command injection
5:05 Conclusion