NEW350+ rooms now have a live terminal, so you can learn by typing the commands, right in your browser.Learn in a live terminal. 350+ rooms.Try a lab♥ Codelivly is 100% free, no paywall. If it helped you, chip in to keep it running.100% free. Help keep it so.Support us
[>_] ROOM · Cybersecurity
Guided Lab: Injecting a Chatbot via a Malicious Document
A hands-on lab demonstrating how to weaponize document uploads to perform indirect prompt injection against an enterprise RAG chatbot.
Room tasks
1Lab Setup and Target Overview: The DocuQuery AI Environment
2Crafting the Malicious Document Payload
3Executing and Verifying the Injection
Frequently Asked Questions
What is indirect prompt injection?
It is when malicious instructions are hidden in external content, such as a document or web page, that an LLM later processes. The model may follow them as if the user had typed them.
How can a PDF attack a chatbot?
If a chatbot reads uploaded files, hidden text in a PDF can contain instructions that alter its behavior or leak data. The user may never see the injected content.
Is the lab safe to try?
Yes. It runs in a controlled environment on Codelivly, so you can practise weaponizing a document without touching real systems. The guided lab is free and hands-on.