
exploitgym
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.


AI / LLM Red Team Field Manual & Consultant’s Handbook

Automating Host Exploitation with AI

Protection against Model Serialization Attacks

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

AI 驱动的 SOC 仿真平台


reverse engineering SynthID for text


PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…

Tools for attacking Computer Use Agents

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

Official repository for CTFTiny

Google Tensor Cracks