gmh5225/llm-attack-promptJailbreaks,Prompt Leaks,Prompt Injection,LLM Attack.Large language model attack prompt collection
A comprehensive collection of Large Language Model (LLM) attack techniques, prompts, and security research materials. This repository serves as a centralized resource for understanding and studying various methods used to exploit or bypass LLM safety mechanisms.
The latest large language model injection and jailbreak methods, you can try to check yourself.
This repository contains curated content related to:
jailbreaks/ - Collection of jailbreak prompts and techniquesprompt_injection/ - Prompt injection attack examples and methodssystem_prompt/ - System prompt extraction and analysisYou can visit index.json to get the complete data list and the corresponding file address. categories is the directory to which the file belongs.
{
"update_time": "2025-06-20T14:01:00Z",
"categories": {
"jailbreaks": {
"description": "LLM Jailbreaks",
"count": 5,
"files": [
{
"file_name": "directive_7.0_20250620.txt",
"last_updated": "2025-06-20T10:14:09Z"
},
{
"file_name": "recursive_mirror_20250620.txt",
"last_updated": "2025-06-20T10:16:27Z"
},
{
"file_name": "evil_writer_20250620.txt",
"last_updated": "2025-06-20T10:01:11Z"
},
{
"file_name": "sophia_20250620.txt",
"last_updated": "2025-06-20T10:00:02Z"
},
{
"file_name": "dan_20250619.txt",
"last_updated": "2025-06-19T15:49:19Z"
}
]
},
"prompt_injection": {
"description": "Prompt Injection",
"count": 2,
"files": [
{
"file_name": "label_replacement_20250619.txt",
"last_updated": "2025-06-19T15:34:28Z"
},
{
"file_name": "ignore_previous_directions_20250619.txt",
"last_updated": "2025-06-19T15:39:10Z"
}
]
},
"system_prompt": {
"description": "System Prompt",
"count": 2,
"files": [
{
"file_name": "safe_bot_20250620.txt",
"last_updated": "2025-06-20T10:28:11Z"
},
{
"file_name": "kali_gpt_20250619.txt",
"last_updated": "2025-06-19T15:02:56Z"
}
]
}
}
}
This collection is intended for:
The content in this repository is provided for educational and research purposes only. Users are responsible for ensuring ethical and legal use of these materials.
Keywords: Jailbreaks, Prompt Leaks, Prompt Injection, LLM Attack, AI Security, Large Language Models