A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.
A framework for cyber defenders to perform adversary infrastructure pivots and reveal additional adversary infrastructure.
A curated list of useful resources that cover Offensive AI.
A toolkit demonstrating security vulnerabilities in MCP frameworks through various attack vectors, for educational purposes.
Project Mantis is a tool designed to counter LLM-driven cyberattacks using prompt injection techniques.
Discover the OWASP Top 10 security risks for Large Language Models and Generative AI, with expert guidance and best practices.
A curated list of GPT agents for cybersecurity.
