Prompt Injection
A curated list of resources for understanding, detecting, and mitigating prompt injection attacks against machine learning models.
What is Prompt Injection?
Awesome Prompt Injection is a curated GitHub repository that serves as an educational hub and resource collection for the cybersecurity vulnerability known as prompt injection. It focuses on attacks that target machine learning models, particularly large language models (LLMs), by crafting malicious inputs that trick the model into deviating from its intended behavior. The project aggregates articles, research papers, tools, tutorials, and community links to help practitioners understand, detect, and defend against these threats.
AI/ML developers, application security engineers (AppSec), red teamers, and security researchers who are building or securing applications that integrate LLMs and AI agents. It is also valuable for anyone involved in AI safety and adversarial machine learning.
It provides a single, continuously updated source of truth for a complex and rapidly evolving security threat. Instead of scattered research, developers get a vetted collection of practical resources, hands-on challenges, and links to authoritative standards, significantly accelerating their learning and implementation of defenses.
Overview
Learn about a type of vulnerability that specifically targets machine learning models
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
