Claude Security Research Skill

🔐 Claude Security Research Skill

  

**A full-spectrum security research skill for Claude** — structured, tool-driven security assessment workflows built directly into your AI assistant.

Drop this skill into [Claude Code](https://claude.ai/code) or any Claude MCP setup and get an AI that thinks like a security researcher: structured phases, proper tool chaining, scoped recon, and professional reporting — not ad-hoc command generation.

Claude's role in this skill is to **interpret tool output, suggest next steps, and document findings**. Tools perform the active testing. Claude does not generate payloads or exploit code.

---

See It In Action

Want to know what the output actually looks like before installing?

**[View sample assessment report →](examples/sample-report.md)**

A fictional but realistic security assessment report showing the exact format Claude produces — five findings across CRITICAL → INFO severities, with raw tool output, impact analysis, and a remediation priority table.

---

What It Does

The skill gives Claude a complete engagement workflow across 6 phases:

RECON → ENUMERATION → VULN SCANNING → VULNERABILITY VALIDATION → SECRETS AUDIT → REPORTING

Claude automatically routes based on your target type, loads the right reference, suggests tools in the right order, and hands off outputs between phases.

Supported Targets

Target	Tools Used
Web server (Apache / Nginx / IIS)	nmap, nikto, nuclei, testssl
REST API	ffuf, sqlmap, dalfox
Web application	nikto, nuclei, ZAP, ffuf
Network / IP range	nmap, snmpwalk, enum4linux
Source code / repo	trufflehog
Full engagement	Everything, in phase order

---

Quick Start

0. Prerequisites

• Claude Code installed and configured
• A tar