InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. CL4R1T4S

    Prompts

    LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

    Stale GitHub, elder-plinius 52.5k ★AGPL-3.0Updated 7 days ago

    git clone https://github.com/elder-plinius/CL4R1T4S.git
  2. Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.

    Indexed GitHub, asgeirtj 71.5k ★CC0-1.0Updated yesterday

    git clone https://github.com/asgeirtj/system_prompts_leaks.git
  3. Collection of leaked system prompts for ChatGPT, Claude, Grok, Gemini,Deepseek, Manus, vercel v0,lovable,cursor, etc...

    Stale GitHub, YeeKal 175 ★Updated 6 months ago

    git clone https://github.com/YeeKal/leaked-system-prompts.git
  4. A collection of GPT system prompts and various prompt injection/leaking knowledge.

    Stale GitHub, LouisShark 10.8k ★MITUpdated 7 days ago

    git clone https://github.com/LouisShark/chatgpt_system_prompt.git
  5. Tracking prompts, feature flags and metadata of Claude Code releases. Subscribe to ↓

    Indexed GitHub, marckrenn 900 ★Updated 3 days ago

    git clone https://github.com/marckrenn/claude-code-changelog.git
  6. New updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

    Stale GitHub, zebbern 30 ★Updated 16 months ago

    git clone https://github.com/zebbern/system_prompts_leaks.git
  7. The Claude Mythos 5.1 System Prompt

    Stale GitHub, jungjin0003 64 ★Updated 40 days ago

    git clone https://github.com/jungjin0003/Claude-Mythos-5.1-System-Prompt.git
  8. AI编程工具中文提示词合集,包含Cursor、Antigravity、VSCode Agent等多种AI编程工具的提示词,为中文开发者提供AI辅助编程参考资源。持续更新中文编程Rules和最新AI编程提示词。

    Stale GitHub, Omnls 415 ★MITUpdated 3 months ago

    git clone https://github.com/Omnls/system-prompts-and-models-of-ai-tools-chinese.git
  9. LLM-Jailbreaks

    Prompts

    LLM Jailbreaks, ChatGPT, Claude, Llama, DAN Prompts, Prompt Leaking

    Stale GitHub, langgptai 816 ★Apache-2.0Updated 19 months ago

    git clone https://github.com/langgptai/LLM-Jailbreaks.git
  10. Awesome-AI-GPTs

    Prompts

    Awesome AI GPTs, OpenAI GPTs, GPT-4, ChatGPT, GPTs, Prompts, plugins, Prompts leaking

    Stale GitHub, EmbraceAGI 1,203 ★CC0-1.0Updated 2 months ago

    git clone https://github.com/EmbraceAGI/Awesome-AI-GPTs.git
  11. { "role": "Calm, safety-first home plumbing triage advisor who helps homeowners and renters understand a water leak or plumbing problem from their own description and decide what to do right now, what they can safely…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  12. Develop a memory profiling tool in C for analyzing process memory usage. Implement process attachment with minimal performance impact. Add heap analysis with allocation tracking. Include memory leak detection with…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  13. # Hallucination & Drift Vulnerability Prompt Checker **VERSION:** 1.7.6 **AUTHOR:** Scott Malin, CISSP **PURPOSE:** Identify structural openings, logic leaks, and fragility points in a prompt that invite hallucinations…

    Indexed prompts.chat (CC0 prompt collection), thanos0000@gmail.com CC0-1.0

  14. --- name: add-ai-protection license: Apache-2.0 description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses…

    Indexed prompts.chat (CC0 prompt collection), davidmytton CC0-1.0

  15. Vintage 1980s-style analog photograph, warm faded colors, heavy grain, slight light leak. Iranian woman, thick natural brows, looking up from beneath lowered lashes, one brow subtly raised, a slow blink — coquettish…

    Indexed prompts.chat (CC0 prompt collection), omidzamani2@gmail.com CC0-1.0

  16. # FastAPI Service taste of a Python API engineer - Define request and response bodies with Pydantic v2 models and always set response_model so nothing leaks by accident. Confidence: 0.95 - Keep separate schemas for…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  17. # Machine Learning Experiment taste of an applied ML engineer - Write the evaluation metric and a dumb baseline before training any real model. Confidence: 0.95 - Split data by time or by entity when leakage is…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

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.