Akto is the fastest growing AI Security platform for your teams to secure AI agents, MCPs, LLMs, Agent skills, Gen AI apps in your organization.
Break your AI before they do. Join Discord: https://discord.gg/8A6mFckxZ
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.
Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.
Evidence-driven AI red teaming platform for LLM, RAG, and agentic applications.
Yang Code Review (YCR) - A lightweight GitHub Action for AI-powered, OWASP-aligned code review with your own LLM provider.
AI Coding Hackathon Project - Experimenting with AI-assisted development workflows
Ultra-fast AI reverse proxy with semantic cache, PII masking, budget controls, and smart failover — featuring a stunning TUI dashboard
Curated AI security and safety evaluation benchmarks well-regarded by Frontier AI labs
The world's most comprehensive open-source security knowledge base — 45 guides across 9 domains
Research and defense implementation for prompt injection vulnerabilities in LLM applications
Secure your code in seconds. VibeSafe is an AI-native DevSecOps CLI tool that detects vulnerabilities, secrets, insecure configs, and hallucinated dependencies before they ship.
AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.
OWASP Foundation web repository
A Solution to The Gandalf AI from Lakera. https://gandalf.lakera.ai/ The Gandalf LLM README documents the inputs used to reveal secret passwords through various levels of the Gandalf AI by Lakera, with each input tested multiple times for consistency.
A foundational boilerplate system for attacking LLMs on Ollama via giskard.
OpenGnosis is a red-teaming framework for evaluating the safety boundaries of LLMs.
AI‑Security est une plateforme intelligente dédiée à la sécurité publique et privée. Elle utilise l’analyse comportementale et l’automatisation pour détecter les situations à risque, prévenir les incidents et renforcer la protection des personnes, des lieux et des organisations. AI‑Security = Surveillance intelligente + Analyse en temps réel.
🛡️ EDR-Hunter Pro - AI-Powered Endpoint Detection & Response platform. Real-time monitoring, anomaly detection, and Telegram Bot alerts.
To associate your repository with the ai-security-testing topic, visit your repo's landing page and select "manage topics."