From aj-geddes-useful-ai-prompts-4
Guides ethical hacking and security testing using penetration testing tools, exploit frameworks, and manual validation. Use for assessing application security posture and identifying exploitable vulnerabilities.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aj-geddes-useful-ai-prompts-4:penetration-testingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- [Overview](#overview)
Systematic security testing to identify, exploit, and document vulnerabilities in applications, networks, and infrastructure through simulated attacks.
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)
Detailed implementations in the references/ directory:
| Guide | Contents |
|---|---|
| Automated Penetration Testing Framework | Automated Penetration Testing Framework |
| Burp Suite Automation Script | Burp Suite Automation Script |
npx claudepluginhub joshuarweaver/cascade-code-languages-misc-1 --plugin aj-geddes-useful-ai-prompts-4Conducts OWASP-based penetration testing: reconnaissance, Top 10 vulnerabilities (access control, injection, misconfig), API security, PoCs, code remediations, reports. For security audits.
Guides scoping and executing penetration tests, including defining rules of engagement, selecting methodology, and building remediation processes for compliance.
Orchestrates a penetration test by routing user intent to 25 specialized skills covering authorization, scanning, and reporting.