Skip to main content
skill CX Codex

pentest-lyan — Claude Code skill: what it does, how to install

pentest-lyan-web-security-testing is a Claude Code skill for web penetration testing: it models threats, reads frontend JavaScript and checks whether one role can reach past another.

no license 166 installs ★ 13 updated 2026-10-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add reason-machines/security-skills --skill pentest-lyan-web-security-testing -a claude-code
Open on GitHub

What pentest-lyan-web-security-testing does

The run goes in three stages: discovery, attack, audit. Discovery means reading the frontend JavaScript to work out request signing, parameters and business rules before anything is sent at the API. Threats come from 12 angles, among them authentication, access control, input handling, file uploads and third-party dependencies.

A finding only counts once the effect on data is confirmed — a record really changed, a state really moved. You declare each account's role_level (high_privilege, standard, limited) yourself; the skill builds a permission matrix from those and tests crossings. Progress is kept in pentest-data/<project-id>/, so --resume picks up an interrupted run and --list shows what is already there.

Python 3.8+ with the project dependencies is the baseline. Playwright MCP adds browser automation and session pooling; without it the skill falls back to curl. Credentials sit in plaintext under pentest-data/, so that folder belongs in .gitignore before the first run. Reports come out twice: Markdown for technical detail, Word for handover.

What it helps with

  • run a web pentest without keeping a manual checklist
  • catch privilege escalation between an admin and a regular user
  • prove a bug changes stored data instead of only returning HTTP 200
  • resume an interrupted run from the saved state
  • hand a Word report to the client and Markdown notes to the team

Example prompts for the agent

  • Run pentest-lyan against my staging build and show me where access breaks between roles.
  • Pick up the last pentest-lyan run with --resume <project-id>.
  • Start pentest-lyan with two logins: admin at role_level: high_privilege and user1 at role_level: standard.

How to install pentest-lyan-web-security-testing

1Skills CLI (Vercel)

npx skills add reason-machines/security-skills --skill pentest-lyan-web-security-testing -a claude-code

2Manually: put the files in place

~/.claude/skills/pentest-lyan-web-security-testing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/pentest-lyan-web-security-testing/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about pentest-lyan-web-security-testing

How do I install pentest-lyan in Claude Code?

Run npx skills add reason-machines/security-skills --skill pentest-lyan-web-security-testing -a claude-code. The skill then sits at ~/.claude/skills/pentest-lyan-web-security-testing/SKILL.md.

What does pentest-lyan do?

It drives an autonomous web app assessment through three stages, reads frontend code before hitting the API, and confirms findings by the change they cause in data. You get both a Markdown and a Word report.

How many accounts does the test need?

Two or more for full cross-role checks. With one account or none the skill runs in a reduced mode and, if it finds a signup page, asks you to create more. Role level is always stated by the user.

Similar skills

All skills for Security →

From the same set129

The whole set →
pentesting-checklist-platform pentesting-checklist-platform gives the agent a structured checklist with over a thousand security checks across 23 platforms, from web and API to Kubernetes and LLM. CX Codex +1 177installs claude-code-cybersecurity-skill claude-code-cybersecurity-skill — a 15-skill collection for security work, covering reconnaissance, malware analysis, threat hunting, incident response, and defensive operations. CX Codex +1 174installs spoof-suite-security-hardware spoof-suite-security-hardware configures device identity masking, network spoofing, and browser fingerprint randomization through the hardsp00fd daemon. CX Codex +1 172installs octoguard-openclaw-security-supervision octoguard-openclaw-security-supervision — a skill that walks you through deploying OctoGuard, a gateway in front of OpenClaw that blocks risky tool calls, tracks token spend and keeps an audit trail. CX Codex +1 168installs jamboree-android-security-sandbox jamboree-android-security-sandbox is a Claude Code skill that sets up Android security testing environments with Magisk, Burp Suite, Objection, and a rooted emulator. CX Codex +1 156installs android-mobile-security-sandbox-jamboree The android-mobile-security-sandbox-jamboree skill guides setup of an Android app security environment using Magisk, Burp Suite, Objection, and Frida. Use it to inspect app traffic and runtime behavior. CX Codex +1 155installs jamboree-android-security-testing jamboree-android-security-testing — a skill that assembles an Android pentest rig: rooted emulator, Magisk, Burp Suite traffic interception and Objection/Frida hooks. CX Codex +1 149installs azure-security-lab-terraform azure-security-lab-terraform guides an agent through deploying a Terraform lab in Azure: hub-spoke VNets, Azure Firewall Basic, NSGs and Key Vault. Useful when you want real network controls to practise on without wiring them by hand. CX Codex +1 134installs

Project sponsors

Companies that keep this analytics open