zebbern/system_prompts_leaks

New updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

31
/ 100
Emerging

This project provides a collection of known "system prompts" that have been successfully extracted from popular chatbots like ChatGPT, Claude, and Gemini. It offers examples of what kinds of inputs can reveal a chatbot's hidden instructions, giving you insight into how these AI models are internally configured. This resource is useful for anyone researching chatbot behavior, evaluating AI safety, or developing their own conversational AI.

No commits in the last 6 months.

Use this if you want to understand or test the security and transparency of large language models by trying to expose their underlying system prompts.

Not ideal if you're looking for prompts to use in your own applications to instruct a chatbot on a task, as these are for extracting internal configurations, not for general-purpose interaction.

AI Safety Chatbot Security Prompt Engineering Research AI Ethics LLM Evasion
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 15 / 25

How are scores calculated?

Stars

26

Forks

5

Language

License

Last pushed

Jul 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/zebbern/system_prompts_leaks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.