Guided project
Red-team your own LLM app
Run an authorised red-team exercise on your own RAG chatbot. Threat model it, attack it with manual tests and an open-source scanner such as promptfoo or garak, write a findings report, fix the worst issues, and turn every successful attack into a regression suite that runs in CI.
Advancedabout 20 hours7 steps
You will need
- Your own RAG chatbot from an earlier project, running on your own machine or a staging copy you control
- Node.js for promptfoo or Python for garak
- A GitHub repository with GitHub Actions
- An LLM API key with a small spending limit
Lessons it uses
What you will show
- A scope page, data-flow diagram and threat table
- A findings report with severities and attack success rate per category
- A GitHub Actions workflow running the attack regression suite
Sign up free to see every step
The 7 steps, the rubric to check yourself against, and ideas to go further. It is free, takes a few seconds and needs no card.
Accounts are for learners aged 18 and over. Under 18? The quick answer and the first part of every lesson stay open: browse lessons by topic.