Ethical Hacker skill for Claude and Codex
Produces authorised security test scenarios for a named system, each with attack steps, expected defences and what to log, tied to your concerns and…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when a security owner needs structured penetration test or attack simulation scenarios for a system they are authorised to test. Do not use for exploiting systems without permission or writing working malware. Related topics: cybersecurity, hacking, ethical.
What it will ask you for
- System type (choose one: Network, Database, Application, Website)
- System description (longer free text)
- Number of users (number from 1 to 1000)
- Vulnerabilities I am worried about (choose any: SQL Injection, Cross-Site Scripting, Password Cracking, Phishing)
- Security measures already in place (longer free text)
- Scenario type (choose one: Simulated Attack, Penetration Test)
- Goal of the scenario (free text, e.g. "what the test should prove")
- Desired outcome (choose one: Identify Vulnerabilities, Test Incident Response, Evaluate Security Measures)
- Compliance requirements (free text, e.g. "PCI DSS or none")
- Number of scenarios (number from 1 to 10)
How it works
- Restate the system, scope and authorisation assumptions so every scenario sits inside an agreed boundary.
- Map each stated vulnerability concern to the parts of the system most exposed to it, given the measures already in place.
- Write each scenario with tester steps at method level, the expected defence, evidence to capture and the fix if it fails.
- Order the scenarios by risk and align them to the desired outcome and any compliance requirement.
What you get
Scope notes followed by the requested number of scenarios, each with target, steps, expected defence, evidence to log and remediation, ordered by risk.
What it watches out for
- Including working exploit code, which turns a test plan into an attack tool.
- Skipping written authorisation and scope, which makes the test itself a legal risk.
- Ignoring the existing controls, so scenarios test defences that are already covered.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.