awesome-ai-security-reference — Claude Code skill: overview and setup
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.
no license 248 installs ★ 13 updated 2026-10-09
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a claude-codeWhat awesome-ai-security-reference 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.
What it helps with
- 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 for the agent
- 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?
How to install awesome-ai-security-reference
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a claude-code2Manually: put the files in place
~/.claude/skills/awesome-ai-security-reference/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/awesome-ai-security-reference/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a codex2Manually: put the files in place
.agents/skills/awesome-ai-security-reference/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a cursor2Manually: put the files in place
.cursor/skills/awesome-ai-security-reference/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/security-skills skills/awesome-ai-security-reference2Manually: put the files in place
.github/skills/awesome-ai-security-reference/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/security-skills --path skills/awesome-ai-security-referenceManually: put the files in place
.devin/skills/awesome-ai-security-reference/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about awesome-ai-security-reference
How do I install awesome-ai-security-reference in Claude Code?
Run npx skills add reason-machines/security-skills --skill awesome-ai-security-reference -a claude-code. The skill file is at ~/.claude/skills/awesome-ai-security-reference/SKILL.md.
What does awesome-ai-security-reference do?
It helps you navigate AI security learning resources and testing tools, covering topics from ML foundations and prompt injection to privacy attacks and AI-assisted pentesting.
Does the skill need an API key?
The reference itself points to resources and tools. Its ai_evaluation example uses the OPENAI_API_KEY environment variable.