yunwei37/prompt-hacker-collections
prompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记
This project helps security professionals and researchers understand and defend against prompt injection attacks on Large Language Models (LLMs) like ChatGPT. It provides a curated collection of example prompts and techniques for 'jailbreaking' LLMs, along with methods for reverse engineering and defending against such attacks. The input is various prompts, and the output is a deeper understanding of LLM vulnerabilities and defenses.
295 stars. No commits in the last 6 months.
Use this if you are a security professional, researcher, or student focused on understanding and mitigating risks associated with AI safety and prompt injection in large language models.
Not ideal if you are looking for a software tool or API to directly integrate into an existing application for automated prompt defense.
Stars
295
Forks
32
Language
—
License
MIT
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/yunwei37/prompt-hacker-collections"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
protectai/llm-guard
The Security Toolkit for LLM Interactions
MaxMLang/pytector
Easy to use LLM Prompt Injection Detection / Detector Python Package with support for local...
utkusen/promptmap
a security scanner for custom LLM applications
agencyenterprise/PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a...
Resk-Security/Resk-LLM
Resk is a robust Python library designed to enhance security and manage context when...