# kali-pentest-ai-agent

This skill plans and runs phased penetration tests with Kali Linux tools. It fits authorized assessments where high-risk actions need human approval.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 837 installs · ★ 12
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/kali-pentest-ai-agent/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/kali-pentest-ai-agent

## What it does

kali-pentest-ai-agent guides an agent through reconnaissance, scanning, vulnerability checks, exploitation, and post-exploitation. It selects Kali utilities from the test context, carries findings between phases, and adjusts the next steps as results arrive. The package describes 269 CLI tools, scenario playbooks for different assessment types, and Quick, Standard, and Deep modes.

The workflow checks authorization and scope, then pauses for approval before high-risk actions. Results can be turned into Markdown or HTML reports containing evidence and remediation guidance. Kali can run on the local machine, through SSH, or in Docker; remote access needs an SSH key, while the container mode needs Docker. Without an accessible Kali environment, the agent cannot run the assessment.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills kali-pentest-ai-agent
```

2. **Manually: put the files in place**
- File: `.github/skills/kali-pentest-ai-agent/SKILL.md`

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

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

## When to use it
- plan a phased penetration test
- scan a network for exposed services
- connect reconnaissance findings to later checks
- assess a web application for vulnerabilities
- produce a report with evidence and remediation

## Example prompts
- Run `/kali-pentest` for an authorized quick scan of `10.0.0.0/24` using the local Kali environment.
- Use Docker mode to assess `http://192.168.1.50`; the `kali-pentest` container is ready and authorization is confirmed.
- Perform a deep assessment of `192.168.1.50` through Kali over SSH, starting with port discovery and ending with a report.

## Similar
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 57000 installs
- [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · 45400 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 54800 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 70200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 42 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