The Security Toolkit for LLM Interactions

a security scanner for custom LLM applications

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

This repository provides a benchmark for prompt injection attacks and defenses

Self-hardening firewall for large language models

Dropbox LLM Security research code and results

gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。

Developer-First Open-Source AI Security Platform - Comprehensive Security Protection for AI Applications

The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.

This class is a broad overview and dive into Exploiting AI and the different attacks that exist, and best practice strategies.

Code scanner to check for issues in prompts and LLM calls

A prompt injection game to collect data for robust ML research

RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered applications, including chatbots, virtual assistants, and knowledge retrieval systems.

Manual Prompt Injection / Red Teaming Tool

Whispers in the Machine: Confidentiality in Agentic Systems

Easy to use LLM Prompt Injection Detection / Detector Python Package

LLM Security Platform.