# awesome-ai-security-reference

The awesome-ai-security-reference skill points to learning resources and tools for AI security, from prompt injection to privacy attacks. Use it to explore a topic or find ways to test a model.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 248 installs · ★ 13 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/awesome-ai-security-reference/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/awesome-ai-security-reference

## What it does

The skill is a guide to resources on machine-learning and large-language-model security. Its subject areas include ML foundations, prompt injection, adversarial examples, data poisoning and backdoors, privacy attacks, LLM testing, and AI-assisted pentesting. Ask it to explain a security topic or help locate testing tools.

The collection names tools such as Garak, Rebuff, Counterfit, and NeMo Guardrails, alongside courses, papers, and other reading. This is a reference guide, not a scanner that runs tests by itself. Some examples rely on separate tools; the `ai_evaluation` example uses the `OPENAI_API_KEY` environment variable. To browse the reference locally, clone it with `git clone https://github.com/muellerberndt/awesome-ai-security.git`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/awesome-ai-security-reference/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/awesome-ai-security-reference/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/awesome-ai-security-reference/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/awesome-ai-security-reference/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/awesome-ai-security-reference
```

2. **Manually: put the files in place**
- File: `.github/skills/awesome-ai-security-reference/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/security-skills --path skills/awesome-ai-security-reference
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/awesome-ai-security-reference/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/security-skills/tree/HEAD/skills/awesome-ai-security-reference/SKILL.md

## When to use it
- find study materials on ML security fundamentals
- learn about prompt injection attacks and defenses
- choose tools for checking LLM vulnerabilities
- research privacy attacks and data poisoning

## Example prompts
- Find learning resources that introduce machine-learning security.
- Explain ways to test an LLM for prompt injection weaknesses.
- Which tools can I use to assess model attacks and defenses?

## Similar
- [llm-security](https://affpapa.org/en/nevibecode/skills/llm-security.md) — skill · 1800 installs
- [16-ai-llm-security](https://affpapa.org/en/nevibecode/skills/16-ai-llm-security.md) — skill · ★ 71 repo stars
- [bug-bounty](https://affpapa.org/en/nevibecode/skills/bug-bounty.md) — skill · 682 installs
- [Large Language Models Security Specialist](https://affpapa.org/en/nevibecode/prompts/large-language-models-security-specialist.md) — prompt · ★ 178201 repo stars
- [agent-security-audit](https://affpapa.org/en/nevibecode/skills/agent-security-audit.md) — skill · 302 installs
- [ai-system-testing](https://affpapa.org/en/nevibecode/skills/ai-system-testing.md) — skill · 1400 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 129 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
