x-glacier

x-glacier / kali-pentest

Public

AI agent skill for autonomous penetration testing via Kali Linux — 199 CLI tools, 15 scenario playbooks, depth-enforced workflows over SSH or Docker. Works with Claude Code, OpenClaw, and Hermes Agent.

ai-agent claude-code-skill cybersecurity ethical-hacking hermes-agent
10
3
100% credibility
Found May 07, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

Documentation and guides for an AI agent skill that automates authorized penetration testing workflows using Kali Linux CLI tools across 14 categories including networks, web, cloud, wireless, and forensics.

How It Works

1
👀 Discover the Helper

You hear about a smart AI assistant that safely checks computers and networks for weak spots using trusted testing methods.

2
📁 Add It to Your AI

Simply copy the folder into your AI friend's skills area, and it's ready to use like any other helpful tool.

3
🔗 Connect Your Test Setup

Tell the AI the safe address and private key for your testing computer, so it can reach the tools securely.

4
🎯 Give It a Security Job

Describe what to test, like a network or website, confirm you have permission, and watch it plan the best way.

5
🔍 Watch It Work

The AI picks the right checks, runs them step by step, adapts as it learns, and pauses for your okay on big steps.

📊 Enjoy Your Report

Get a clear, detailed summary of every finding with proof pictures, risk levels, and easy fix steps.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is kali-pentest?

This GitHub repo agent skill turns AI agents like Claude Code, OpenClaw, or Hermes into autonomous pentesting machines using Kali Linux's 199 CLI tools over SSH or Docker. Drop it into your agent's skills folder, point it at a Kali server or container, confirm authorization, and it runs depth-enforced workflows across 15 scenario playbooks for web apps, AD, cloud-native, wireless, and more—generating structured reports with evidence. It's like a kali linux pentesting bible pdf distilled into agent skills claude can execute hands-free.

Why is it gaining traction?

Unlike manual tool chaining or basic agent github copilot cli wrappers, it enforces testing depth via coverage matrices, zero-findings fallbacks, and objective stopping conditions, preventing shallow scans. Agent skills anthropic users get plug-and-play compatibility with claude-sonnet-4.6 or local models, plus cross-scenario handoffs (e.g., web scan spotting AD). In the agent skills github space, its layered docs and playbook graph stand out for reliable, auditable automation over ad-hoc agent github code.

Who should use this?

Red teamers automating pentests with agent skills claude or OpenClaw, especially for internal networks, API security, or cloud assessments where depth matters. Pentesters evaluating agent skills repo for SSH/Docker Kali integration, or security devs building agent skills library around github agent hq workflows. Skip if you're not running AI agents like agent github copilot vscode extensions.

Verdict

Promising early agent skills standard for autonomous Kali pentests, with excellent docs and playbook coverage—install and test on a lab target today. At 10 stars and 1.0% credibility score, it's immature with no tests visible, so validate outputs manually before client work.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.