Skip to content
Get packs

Internal Network Penetration Test

Walks an agent through simulated insider or post-breach attacks on a corporate internal network.

Source Download skill
Repository
mukul975/Anthropic-Cybersecurity-Skills
Stars
35,430
Licence
Apache-2.0
Files
7 files

What it does

This skill gives an AI agent a detailed playbook for testing a company's internal network as if an attacker had already gotten a foothold on one ordinary employee computer. The agent gets step-by-step guidance and command examples for discovering hosts and services, enumerating Active Directory, capturing and cracking credentials, moving laterally between machines, and escalating privileges, with the goal of showing how far a single compromised device could reach. It also includes two Python helper scripts that run scanning tools such as nmap and produce output for reporting.

Great for

  • Security professionals running an authorized internal penetration test under signed Rules of Engagement
  • Students or trainees learning how lateral movement and Active Directory attacks work in a lab
  • Blue teams wanting to understand attacker paths so they can verify controls and detections

Skip it if

  • Testing any network you do not own or lack written permission to test, since the activity is illegal and the skill gives no authorization checks of its own
  • Production networks without coordination with IT and SOC teams, because scans, password spraying and credential attacks can cause lockouts, outages or alerts
  • Non-technical users looking for a simple tool, since the content assumes familiarity with Kali Linux, nmap, Impacket and Active Directory

Try asking

  • “Plan an assumed-breach internal network test for our corporate VLAN, starting from a standard domain user account”
  • “Give me the enumeration steps for an Active Directory domain using a low-privilege test account and BloodHound”
  • “Explain which lateral movement paths an attacker could take from a single compromised workstation and how to document them”
  • “Draft a checklist of Phase 1 to Phase 3 activities for an internal pentest report”
Step-by-step guide: how to use Internal Network Penetration TestInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 7 original files, the Apache-2.0 licence and an attribution note.

    conducting-internal-network-penetration-test.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip conducting-internal-network-penetration-test.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip conducting-internal-network-penetration-test.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Only run this with signed Rules of Engagement that define scope, time windows and emergency contacts, and confirm the target ranges before any scan.
  • Review scripts/agent.py and scripts/process.py before executing them, and replace the hard-coded example credentials and IP ranges with your own authorized values.
  • Ask the agent to use low-impact options first (host discovery, quick scans, BloodHound collection) and to avoid password spraying or credential-capture tools unless the scope explicitly allows them.

What's inside

  • assets/template.md
  • references/api-reference.md
  • references/standards.md
  • references/workflows.md
  • scripts/agent.py
  • scripts/process.py
  • SKILL.md

Redistributed unmodified from mukul975/Anthropic-Cybersecurity-Skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.