
MMSkillRisk
Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

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

AI Smart Contract Security Analysis and PoC Generation Framework

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Reverse Shell Detection with Machine Learning

VEDAS-Driven Autonomous Generation + Community Contributions of Suricata & Nuclei Rules for over 15k CVEs

AI 驱动的 SOC 仿真平台

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

Air-gapped cybersecurity assistant for security professionals. 100% offline AI-powered analysis tool for Nmap, Volatility, BloodHound, Metasploit,…

image scaling attacks for multi-modal prompt injection

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Metasploit for machine learning.


GyoiThon is a growing penetration test tool using Machine Learning.

An interactive CLI application for interacting with authenticated Jupyter instances.

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

Automating Host Exploitation with AI

An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.