AI Security Guide

A comprehensive skill for understanding and working with AI security concepts, from machine learning fundamentals to advanced adversarial attacks and defensive frameworks.

When to Use This Skill

Use this skill when the user needs help with:

• Understanding AI/ML algorithms and their security implications
• Learning about AI security frameworks (OWASP ML Top 10, Google SAIF)
• Analyzing or defending against prompt injection attacks
• Understanding model RCE vulnerabilities
• Working with AI Model Context Protocol (MCP)
• Using AI for security tasks like fuzzing and vulnerability discovery
• Understanding LLM architecture from a security perspective
• Any AI-related security assessment or research

Core Concepts

Machine Learning Fundamentals