Skills
.Work. You
Rest

agentic-pentest

Community

LLM-driven autonomous pentest orchestration.

Software Engineering#automation#verification#llm#framework#evidence#pentest
Authorbrucesongs
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables automated, autonomous penetration testing operations guided by LLMs, enabling structured reasoning, tool delegation, and HITL governance across complex engagements.

Core Features & Use Cases

  • Autonomous recon and enumeration: orchestrates multi-step reconnaissance with safe, scoped tool usage and evidence collection.
  • Multi-agent orchestration with MCP: coordinates planner/executor teams and MCP servers for scalable pentesting workflows.
  • Verification and hallucination control: integrates independent verification pipelines, cost tracking, and HITL checkpoints to ensure reproducible findings.
  • Use Case: run a six-phase agentic pentest against a scoped target, producing an auditable report with validated findings and detection-rule extraction.

Quick Start

Prime the engagement context and launch the framework against a scoped target to begin autonomous pentesting.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agentic-pentest
Download link: https://github.com/brucesongs/kali-claw/archive/main.zip#agentic-pentest

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.