Curated + custom prompt injections for AI models, focusing on security and exploit development.
Explore prompt injection techniques in large language models (LLMs), providing examples to improve LLM security and robustness.
A benchmark for prompt injection detection systems, providing a neutral way to evaluate their performance.
This repository provides a benchmark for prompt Injection attacks and defenses.
Every practical and proposed defense against prompt injection.
The Security Toolkit for LLM Interactions, ensuring safe and secure interactions with Large Language Models.
A prompt injection scanner for custom LLM applications.
A guide for understanding and mitigating prompt attacks on large language models.
PFI is a system designed to prevent privilege escalation in LLM agents by enforcing trust and tracking data flow.
Breaker AI is an open-source CLI tool for security checks on LLM prompts.
Breaker AI is a CLI tool that detects prompt injection risks and vulnerabilities in AI prompts.
A novel approach to hacking AI assistants using Unicode Tags to bypass security measures in large language models.
AISecKit
