# Jailbreaking

> Jailbreaking: Getting a model past its safety features. OWASP treats it as a form of prompt injection.

Canonical: https://llmdojo.dev/glossary/jailbreak

Also called jailbreak, jailbreaks.

Getting a model past its safety features. OWASP treats it as a form of prompt injection.

Learn it in the lesson: [Direct injection and jailbreaking](https://llmdojo.dev/learn/prompt-context-engineering/prompt-injection/direct-injection) (Prompt and Context Engineering · Prompt Injection and Trust Boundaries).

## Interview questions about Jailbreaking

- [What's the difference between a jailbreak and a prompt injection?](https://llmdojo.dev/interview/q/what-s-the-difference-between-a-jailbreak-and-a-prompt-injection)
- [Design an ML system that detects harmful content in both the prompts users send to an LLM and the responses it gives.](https://llmdojo.dev/interview/q/design-an-ml-system-that-detects-harmful-content-in-both-the-prompts)

## Related
- [Prompt injection](https://llmdojo.dev/glossary/prompt-injection)
- [Indirect prompt injection](https://llmdojo.dev/glossary/indirect-prompt-injection)
- [Trust boundary](https://llmdojo.dev/glossary/trust-boundary)
- [Glossary of every term](https://llmdojo.dev/glossary)