# ai-security-knowledge-base

ai-security-knowledge-base connects an AI security reference base directly to your coding assistant. It covers threat modeling, OWASP LLM Top 10 vulnerabilities, and model defense tactics.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 332 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/ai-security-knowledge-base/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/ai-security-knowledge-base

## What it does

This skill gives Claude Code access to curated reference materials on machine learning security. The underlying repository covers neural network architectures and reinforcement learning mechanics. It also details the OWASP LLM Top 10 list, explaining prompt injections and training data poisoning.

The files live in the `AI_Security_Top` Markdown documentation set. Topics include Model Context Protocol weaknesses and threat hunting scripts using Isolation Forest. The original documents are in Chinese. Claude Code translates and extracts relevant guidance during the conversation.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill ai-security-knowledge-base -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/ai-security-knowledge-base/SKILL.md

## When to use it
- Review vulnerabilities listed in the OWASP LLM Top 10
- Inspect Model Context Protocol setups for tool poisoning risks
- Build network traffic anomaly detectors using Isolation Forest
- Analyze security log patterns with pre-trained language models

## Example prompts
- Explain how to protect an agent workflow against indirect prompt injection.
- Show defensive guidelines for securing MCP tool configurations.
- Help me detect anomalous server traffic using Isolation Forest.

## 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
- [multi-agentic-threat-model](https://affpapa.org/en/nevibecode/skills/multi-agentic-threat-model.md) — skill · 188 installs
- [Security Planner](https://affpapa.org/en/nevibecode/agents/security-planner.md) — subagent · ★ 1627 repo stars
- [senior-security](https://affpapa.org/en/nevibecode/skills/borghei-senior-security.md) — skill · 203 installs
- [Security Architect](https://affpapa.org/en/nevibecode/skills/security-architect.md) — skill · 175 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
