Jailbreak Detection

LLM Jailbreak Detection

Detect and prevent jailbreak attacks targeting every major LLM. Real detection examples, affected model tables, and step-by-step prevention strategies.

21
Detection Guides
8
AI Labs Covered
9
Techniques Documented

OpenAI

6 guides for OpenAI jailbreak detection

Severe RiskChatGPT

Jailbreak Prompts

ChatGPT jailbreak prompts are carefully crafted inputs designed to bypass OpenAI's safety guidelines and content policies, making the model generate responses it would normally refuse.

Wardstone resultFlagged: Prompt attack
View detection guide
Severe RiskChatGPT

DAN Jailbreak

The DAN (Do Anything Now) jailbreak is one of the most well-known ChatGPT exploits, instructing the model to adopt an unrestricted alter-ego that ignores all safety guidelines.

Wardstone resultFlagged: Prompt attack
View detection guide
Severe RiskChatGPT

Prompt Injection

ChatGPT prompt injection is an attack where malicious instructions are embedded in user input to override the system prompt and manipulate the model's behavior.

Wardstone resultFlagged: Prompt attack
View detection guide
Severe RiskChatGPT

Developer Mode Jailbreak

The Developer Mode jailbreak tricks ChatGPT into believing it has entered a special diagnostic mode where content policies are suspended for testing purposes.

Wardstone resultFlagged: Prompt attack
View detection guide
Severe RiskChatGPT

System Prompt Extraction

System prompt extraction is an attack where adversaries trick ChatGPT into revealing its hidden system instructions, exposing proprietary logic, content policies, and application secrets.

Wardstone resultFlagged: Prompt attack
View detection guide
Severe RiskGPT-5

Jailbreak Attacks

GPT-5 jailbreaks are adversarial prompts designed to bypass the safety guardrails of OpenAI's frontier models, including GPT-5.2 and GPT-5.3-Codex.

Wardstone resultFlagged: Harmful content
View detection guide

Anthropic

4 guides for Anthropic jailbreak detection

Google

2 guides for Google jailbreak detection

xAI

2 guides for xAI jailbreak detection

Microsoft

1 guide for Microsoft jailbreak detection

Meta

2 guides for Meta jailbreak detection

DeepSeek

2 guides for DeepSeek jailbreak detection

General

2 guides for General jailbreak detection

Ready to protect your AI application?

Wardstone Guard detects all these jailbreak techniques in a single API call with Sub-30ms latency.