ctf-ai-ml SKILL.md skillB

ctf-ai-ml from ljagiello/ctf-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add ljagiello/ctf-skills/ctf-ai-ml@git:20261027.2388a3b

Pins git:20261027.2388a3b in mdr.lock. Pin the fingerprint instead.

Audit grade: B, 16 of 17 checks passed
Kind: SKILL.md skill
Repository: ljagiello/ctf-skills
Path: ctf-ai-ml/SKILL.md
Versions recorded: 3
Latest version: git:20261027.2388a3b, committed Oct 27, 2026
First version recorded: Mar 28, 2026
Size: 7,088 bytes
Repository stars: 3,657
License: MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# CTF AI/ML

Quick reference for AI/ML CTF challenges. Each technique has a one-liner here; see supporting files for full details.

## Prerequisites

**Python packages (all platforms):**
```bash
pip install torch transformers numpy scipy Pillow safetensors scikit-learn
```

**Linux (apt):**
```bash
apt install python3-dev
```

**macOS (Homebrew):**
```bash
brew install python@3
```

## Additional Resources

- [model-attacks.md](model-attacks.md) - Model weight perturbation negation, model inversion via gradient descent, neural network encoder collision, LoRA adapter weight merging, model extraction via query API, membership inference attack
- [adversarial-ml.md](adversarial-ml.md) - Adversarial example generation (FGSM, PGD, C&W), adversarial patch generation, evasion attacks on ML classifiers, data poisoning, backdoor detection in neural networks
- [llm-attacks.md](llm-attacks.md) - Prompt injection (direct/indirect), LLM jailbreaking, token smuggling, context window manipulation, tool use exploitation

---

## When to Pivot

- If the challenge becomes pure math, lattice reduction, or number theory with no ML component, switch to `/ctf-crypto`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add ljagiello/ctf-skills/ctf-ai-ml@sha256:5b9911c99ff161de

The line at the top of this page pins the label git:20261027.2388a3b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_6wbfnk2chwkzg27d.svg)](https://markdownregistry.com/a/art_6wbfnk2chwkzg27d)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Mar 28, 2026 and Oct 27, 2026, about one every 106 days.

version	committed	commit	size	audit
git:20261027.2388a3b latest	2026-10-27	2388a3b	7,088 B	B	view · diff
git:20260328.ac4dfd9	2026-03-28	ac4dfd9	7,062 B	B	view · diff
git:20260328.8d978f1	2026-03-28	8d978f1	6,997 B	B	view

Audit of the latest version

B 16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: No prompt-injection phrasing (matched: Ignore previous instructions)
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (7088 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

ljagiello/ctf-skills · 3,657 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6wbfnk2chwkzg27d
GET https://markdownregistry.com/api/v1/resolve?ref=ljagiello/ctf-skills/ctf-ai-ml
GET https://markdownregistry.com/api/v1/blob/5b9911c99ff161de1b584251824b9cccc31c02f6a3e467cae5e503032f55c1a4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ljagiello/ctf-skills

ctf-crypto SKILL.md skill

ljagiello/ctf-skills · ctf-crypto/SKILL.md · Provides cryptography attack techniques for CTF challenges. Use when attacking encryption, hashing, signatures, ZKP…