Claude Security Research Skill
AI-powered security research assistant for Claude Code — structured assessment workflows, tool orchestration, and professional reporting across recon, enumeration,…
Install
pip install trufflehogInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →🔐 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 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 →
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 target you are authorized to test
- Linux/macOS environment (WSL works on Windows)
1. Install the skill
Claude Code (recommended):
# Clone into your Claude skills directory
git clone https://github.com/rhysha/claude-security-research-skill ~/.claude/skills/security-research
Manual / MCP:
Copy SKILL.md and the references/ folder to your Claude skills path.
2. Verify your tools
chmod +x scripts/tool-check.sh
./scripts/tool-check.sh
3. Start an engagement
chmod +x scripts/init-engagement.sh
./scripts/init-engagement.sh example.com
4. Talk to Claude
The skill can be invoked two ways.
As a slash command (Claude Code CLI):
/security-research
This explicitly loads the skill into Claude's context.
As natural language: Claude will also auto-load the skill when your request matches its description — asking for a scan, vuln assessment, recon, secrets audit, etc.:
"Run a full security assessment on https://target.example.com — I have written authorization."
"Do passive recon on domain.com — stay passive only."
"Scan this API for OWASP Top 10 issues: https://api.example.com"
"Audit this repo for leaked secrets."
"Analyze these nmap results and suggest next assessment steps."
Claude will confirm scope, propose a phase plan, load the right references, and walk through the engagement step by step — pointing you at the tool that should run each check.
Skill Structure
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…