Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LLM-Jailbreaks
PromptsLLM Jailbreaks, ChatGPT, Claude, Llama, DAN Prompts, Prompt Leaking
git clone https://github.com/langgptai/LLM-Jailbreaks.git -
ChatGPT-Jailbreak-Prompts
Datasets & benchmarksHugging Face dataset by rubend18
rubend18/ChatGPT-Jailbreak-Prompts -
gpt6-Astra
Promptsgpt6 Astra-claude-grok4.7-deepseekv4.1flash-glm5.3-gemini破甲越狱 · 冷咖啡 BREAK//OPEN 工作台
git clone https://github.com/3641397194-wq/gpt6-Astra.git -
Jailbreaks
PromptsA repo for all the jailbreaks
git clone https://github.com/tuxsharxsec/Jailbreaks.git -
dsh-purge
Prompts基于上游 1.1.71 维护的 dsh-purge 社区兼容包:只负责 DeepSeek Harness 的版本与本地 Windows 运行问题兼容。
git clone https://github.com/555bbbAAA/dsh-purge.git -
dsh-purge-plus
Promptsdsh-purge 的非官方分支(fork):适配 DeepSeek Harness 0.2.1-rc.2、破甲内核 v3、设置页 UI 重做 / unofficial fork of YuJunZhiXue/dsh-purge (MIT)
git clone https://github.com/JeffKeeping/dsh-purge-plus.git -
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
Awesome-Multimodal-Prompts
PromptsPrompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.
git clone https://github.com/langgptai/Awesome-Multimodal-Prompts.git -
Rules.txt
PromptsLLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases
git clone https://github.com/Xayan/Rules.txt.git -
JailbreakHub
PromptsA Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
git clone https://github.com/lalipa2003-arch/JailbreakHub.git -
XGPT-WormGPT
Prompts[New Update](Added Agentic-Mode, Dark-GODMode)The Real BlackHat GPT - ai can do your illegal stuffs without saying anything. Use At Your Own Risk!
git clone https://github.com/gaur-avvv/XGPT-WormGPT.git -
jailbreak-archives
PromptsA structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
git clone https://github.com/e2sy/jailbreak-archives.git -
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git -
Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc
git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.