---
term: "Jailbreak"
category: "AI risks and safety"
url: https://agenticopenfinance.com/glossary/jailbreak
source: AgenticOpenFinance glossary
---

# Jailbreak

> A prompting attack designed to get a model to bypass its safety rules or restrictions.

A jailbreak is a prompting attack designed to make a generative AI model bypass the safety restrictions or usage rules placed on it by its developer or operator, for example through role play, obfuscation or long chains of instructions. NIST's taxonomy of adversarial machine learning treats jailbreaks as a category of attacks on generative models. Because jailbreaks keep evolving, controls that matter for money must not depend on the model refusing.

Related terms: [Prompt injection](https://agenticopenfinance.com/glossary/prompt-injection.md), [System prompt](https://agenticopenfinance.com/glossary/system-prompt.md), [Red-teaming](https://agenticopenfinance.com/glossary/red-teaming.md), [Excessive agency](https://agenticopenfinance.com/glossary/excessive-agency.md)