Solve AI and machine-learning CTF challenges.
What it does
Applies adversarial AI and model-analysis techniques to solve AI/ML capture-the-flag challenges.
When to use it
Use when solving CTF challenges involving model attacks, adversarial examples, prompt injection, inference, poisoning, or LLM jailbreaking.
How to use it
It changes how the agent approaches AI/ML CTF challenges by supplying attack techniques and detailed supporting references.
Latest review
What you need · 8
Requires Python 3.
Requires the torch Python package.
Access · 2
This skill
challenge LLM endpoint
Write
Sends attack prompts to endpoints
torch, transformers, numpy, scipy, Pillow, safetensors, scikit-learn
Execute
Installs AI/ML Python packages