ctf-ai-ml
ctf ai ml
What it does
- llm-attacks.md - Prompt injection (direct/indirect), LLM jailbreaking, token smuggling, context window manipulation, tool use exploitation
- If the challenge becomes pure math, lattice reduction, or number theory with no ML component, switch to /ctf-crypto.
- If the task is reverse engineering a compiled ML model binary (ONNX loader, TensorRT engine, custom inference binary), switch to /ctf-reverse.
- If the challenge is a game or puzzle that merely uses ML as a wrapper (e.g., Python jail inside a chatbot), switch to /ctf-misc.
- Weight perturbation negation: Fine-tuned model suppresses behavior; recover by computing 2Worig - Wchal to negate the fine-tuning delta. See model-attacks.md.
- LoRA adapter merging: Merge LoRA adapter Wbase + alpha (B @ A) and inspect activations or generate output with merged weights. See model-attacks.md.
- Model inversion: Optimize random input tensor to minimize distance between model output and known target via gradient descent. See model-attacks.md.
Requirements & configuration
- llm-attacks.md - Prompt injection (direct/indirect), LLM jailbreaking, token smuggling, context window manipulation, tool use exploitation
- Token smuggling: Exploiting tokenizer splits so filtered words pass through as subword tokens. See llm-attacks.md.
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
ctf-ai-ml FAQ
What does the ctf-ai-ml skill do?
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. llm-attacks.md - Prompt injection (direct/indirect), LLM jailbreaking, token smuggling, context window manipulation, tool use exploitation If the challenge becomes pure math, lattice reduction, or number theory with no ML component, switch to /ctf-crypto.
What does ctf-ai-ml require?
llm-attacks.md - Prompt injection (direct/indirect), LLM jailbreaking, token smuggling, context window manipulation, tool use exploitation Token smuggling: Exploiting tokenizer splits so filtered words pass through as subword tokens. See llm-attacks.md.
How do I install ctf-ai-ml?
Run: npx -y skills add https://github.com/ljagiello/ctf-skills --skill ctf-ai-ml --agent claude-code — the source lives at github.com/ljagiello/ctf-skills.
Maintain ctf-ai-ml?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[ctf-ai-ml on getagentictools](https://getagentictools.com/skills/ljagiello-ctf-skills-ctf-ai-ml?ref=badge) npx agentictools info skills/ljagiello-ctf-skills-ctf-ai-ml The second line is the CLI lookup for this page — handy in READMEs and docs.
