Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
Registry
github (via claudemarketplaces.com)