chatgpt_system_prompt and gptpmt
These are complementary resources: one documents existing GPT system prompts and vulnerability patterns while the other provides best practices for safely engineering prompts, so they address attack and defense sides of prompt security.
About chatgpt_system_prompt
LouisShark/chatgpt_system_prompt
A collection of GPT system prompts and various prompt injection/leaking knowledge.
Organizes extracted system prompts from custom GPTs and ChatGPT instances with indexed searchability via TOC.md and a local `idxtool` script for rapid lookups. Includes security documentation and vulnerability analysis patterns to help developers understand prompt injection attack vectors and defensive techniques. Automatically maintains a table of contents through GitHub Actions workflows, enabling community contributions of newly discovered prompts and exploitation methods.
About gptpmt
CarGod/gptpmt
Prompt Engineering best practices guidebook, written for humans.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work