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: Bypassing a Model's Safety Filter
A hands-on guided lab demonstrating how to chain persona framing and payload obfuscation to bypass strict AI safety filters.
Room tasks
1Lab Setup and Target Guardrail Overview: The CodeGuard AI Environment
2Attempting Multiple Bypass Techniques
3Documenting a Successful Bypass
Frequently Asked Questions
What is a jailbreak?
A jailbreak is a prompt designed to make a model ignore its safety rules and produce restricted output. Techniques include persona framing, role play, encoding and multi-step manipulation.
Why chain multiple techniques?
Single tricks are often detected by filters. Combining persona framing with obfuscation can slip past layered defenses, which is why testers try chains when evaluating safety systems.
Is this lab for learning defense too?
Yes. By seeing how filters are bypassed, you understand where to strengthen them. The lab is free, hands-on and runs in a controlled environment on Codelivly.