Agent Skills: Penetration Testing

Ethical hacking and security testing methodologies using penetration testing tools, exploit frameworks, and manual security validation. Use when assessing application security posture and identifying exploitable vulnerabilities.

UncategorizedID: aj-geddes/useful-ai-prompts/penetration-testing

Install this agent skill to your local

pnpm dlx add-skill https://github.com/aj-geddes/useful-ai-prompts/tree/HEAD/skills/penetration-testing

Skill Files

Browse the full folder contents for penetration-testing.

Download Skill

Loading file tree…

skills/penetration-testing/SKILL.md

Skill Metadata

Name
penetration-testing
Description
>

Penetration Testing

Table of Contents

Overview

Systematic security testing to identify, exploit, and document vulnerabilities in applications, networks, and infrastructure through simulated attacks.

When to Use

  • Pre-production security validation
  • Annual security assessments
  • Compliance requirements (PCI-DSS, ISO 27001)
  • Post-incident security review
  • Third-party security audits
  • Red team exercises

Quick Start

Minimal working example:

# pentest_framework.py
import requests
import socket
import subprocess
import json
from typing import List, Dict
from dataclasses import dataclass, asdict
from datetime import datetime

@dataclass
class Finding:
    severity: str
    category: str
    target: str
    vulnerability: str
    evidence: str
    remediation: str
    cvss_score: float

class PenetrationTester:
    def __init__(self, target: str):
        self.target = target
        self.findings: List[Finding] = []

    def test_sql_injection(self, url: str) -> None:
// ... (see reference guides for full implementation)

Reference Guides

Detailed implementations in the references/ directory:

| Guide | Contents | |---|---| | Automated Penetration Testing Framework | Automated Penetration Testing Framework | | Burp Suite Automation Script | Burp Suite Automation Script |

Best Practices

✅ DO

  • Get written authorization
  • Define clear scope
  • Use controlled environments
  • Document all findings
  • Follow responsible disclosure
  • Provide remediation guidance
  • Verify fixes after patching
  • Maintain chain of custody

❌ DON'T

  • Test production without approval
  • Cause service disruption
  • Exfiltrate sensitive data
  • Share findings publicly
  • Exceed authorized scope
  • Use destructive payloads
Penetration Testing Skill | Agent Skills