Jailbreak

GPTClaudeGemini··▲ 705 copies·updated 2026-07-14

jailbreak.prompt

---
title: Jailbreak Detection
description: Grades whether the user's prompt is an attempt to jailbreak (i.e. generate illegal or harmful responses)
---

Jailbreak detection score is a metric to check if the user prompts to generate a response over potentially harmful or illegal behaviour. 

It can also be used to detect whether a user prompt is not aligned to the model's intented purpose.

You can read our [blog](https://blog.uptrain.ai/llm-jailbreak/) to learn more about what jailbreaks in LLMs.

Columns required:
- `question`: The question asked by the user
- `model_purpose (optional)`: The intended purpose of the LLM

### How to use it?

when to use it

Community prompt sourced from the open-source GitHub repo uptrain-ai/uptrain (Apache-2.0). A "Jailbreak" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.