Claude Pentest Skills

Structured Web Application Penetration Testing with Claude Code

OWASP-based methodology, curated payload references, strict validation gates, and report generation — all orchestrated through slash commands.

Quick Start  |  How It Works  |  Commands  |  Coverage  |  Structure

  6 slash commands  ·  3 agent personas  ·  18 vuln classes
  6-gate validation  ·  OWASP WSTG mapped  ·  PDF report gen

---

The Problem

Pentesting with AI is powerful, but without structure it's chaotic:

• Claude sends payloads to out-of-scope targets
• Findings are false positives that waste report-writing time
• No consistent methodology — different approach every session
• Payload knowledge scattered across bookmarks and notes
• Reports are written from scratch every engagement

The Solution

Claude Pentest Skills is a structured skill pack for Claude Code. It enforces scope, follows OWASP methodology, validates findings through a 6-gate quality process, and generates professional reports — all through simple slash commands.

Before	After
Ad-hoc testing, no structure	OWASP WSTG methodology with coverage tracking
False positives in reports	6-gate validation kills bad findings before they waste your time
"Is this in scope?" uncertainty	Mandatory /scope gate — refuses to test without authorization
Write reports from scratch	/report --full generates professional markdown + PDF
Forget what you tested	Payload log + coverage tracker across sessions
Search PayloadAllTheThings manually	Curated methodology + direct references per vuln class

---

Quick Start

Step 1 — Clone

git clone https://github.com/frendysanusi/claude-pentest-skills.git
cd claude-pentest-skills

Step 2 — (Optional) Set up tools

# Burp Suite MCP
cp .mcp.json.example .mcp.json
# Edit with your local paths

# PDF report generation
python3 -m venv .venv
.venv/bin/pip install markdown weasyprint

Step 3 — Hunt

claude                          # Start Claude Code in the project dir

/scope target.com               # Define authorization (REQUIRED first step)
/recon target.com               # Map attack surface
/hunt injection                 # Test for SQLi, NoSQLi, CMDi, SSTI, XXE
/validate                       # 6-gate quality check
/report --full                  # Generate pentest report

---

How It Works

                         YOU
                          |
                    ┌─────▼─────┐
                    │   Claude  │ <── Burp MCP (optional)
                    │   Code    │
                    └─────┬─────┘
                          |
          ┌───────────────┼───────────────┐
          |               |               |
    ┌─────▼──────┐  ┌──────▼─────┐  ┌─────▼─────┐
    │   Recon    │  │   Hunter   │  │ Validator │
    │   Agent    │  │   Agent    │  │   Agent   │
    └─────┬──────┘  └──────┬─────┘  └─────┬─────┘
          |                |              |
    curl / Burp       payloads/      6-gate check
    JS analysis                      PASS / REJECT
    tech fingerprint                 NEEDS-WORK
          |               |               |
    ┌─────▼───────────────▼───────────────▼──────┐
    │           engagements/<target>/            │
    │                                            │
    │  scope.md · findings.md · payload-log.md   │
    │  coverage.md · tech-stack.md · notes.md    │
    └────────────────────────────────────────────┘
                          |
                    ┌─────▼─────┐
                    │  /report  │ ──> Markdown + PDF
                    └───────────┘

Each command loads the right agent persona, methodology skill, and payload references. State is tracked per engagement in engagements/<target>/.

---

Commands

Command	What It Does
/scope <target>	Define target scope and confirm authorization. Must run first.
/recon <target>	Map attack surface — tech stack, endpoints, input vectors, WAF detection
/hunt <vuln-class>	Test for a specific vulnerability class using OWASP methodology
/validate	Run 6-gate quality check on all unvalidated findings
/report --full	Generate complete pentest report (exec summary, findings, remediation)
/report --finding F-001	Generate report for a single finding
/status	Show engagement dashboard — findings, coverage, payload stats

Hunt Targets

/hunt injection        # SQLi, NoSQLi, CMDi, SSTI, XXE
/hunt auth-access      # IDOR, JWT, OAuth, privilege escalation
/hunt server-side      # SSRF, path traversal, file upload, deserialization
/hunt client-side      # XSS, CSRF, open redirect
/hunt session          # Session fixation, token weakness, cookie security
/hunt business-logic   # Race conditions, workflow bypass, logic flaws
/hunt config           # Headers, CORS, TLS, info disclosure
/hunt ai-llm           # Prompt injection, LLM tool abuse, system prompt leakage

# Or target specific sub-classes:
/hunt sqli             /hunt xss              /hunt ssrf
/hunt idor             /hunt jwt              /hunt prompt-injection

---

Agent Personas

3 specialized personas, each activated by the relevant command:

Agent	Activated By	Personality	Role
Recon Agent	/recon	Systematic, methodical	Maps the full attack surface before exploitation
Hunter Agent	/hunt	Creative, persistent	Tries bypass techniques, iterates on partial success
Validator Agent	/validate	Skeptical, adversarial	Assumes false positive until proven otherwise

When no command is active, Claude behaves as a general security consultant.

---

Validation Gate

Every finding must pass all 6 gates to reach the report. One failure = REJECTED or NEEDS-WORK.

Finding ──> Gate 1: Reproducible PoC?
            Gate 2: HTTP evidence captured?
            Gate 3: Impact verified (not theoretical)?
            Gate 4: Target in scope?
            Gate 5: Real vulnerability (not informational)?
            Gate 6: Client can reproduce it?
                         │
              ┌──────────┼──────────┐
              │          │          │
          VALIDATED   REJECTED  NEEDS-WORK
          (→ report)  (killed)  (fix & retry)

This process eliminates false positives, ensures evidence quality, and produces findings that clients can verify independently.

---

Vulnerability Coverage

Class	Sub-Classes
SQL Injection	Union, blind, time-based, error-based, auth bypass
XSS	Reflected, stored, DOM, CSP bypass, polyglots
SSRF	Internal access, cloud metadata, protocol abuse, IP bypass
SSTI	Jinja2, Twig, Freemarker, Pebble, Mako, ERB
Command Injection	Metacharacters, blind detection, space/quote bypass
XXE	Classic, blind OOB, SVG upload, XInclude, PHP filter
Path Traversal	Encoding bypass, null byte, overlong UTF-8
File Upload	Extension bypass, MIME spoof, magic bytes, polyglots
IDOR	Sequential ID, UUID harvest, GraphQL node, HPP
JWT Attacks	alg:none, RS256→HS256, KID injection, claim tampering
OAuth/OIDC	Redirect URI bypass, state absence, PKCE downgrade
NoSQL Injection	MongoDB operator injection, $regex blind, $where
Deserialization	Java/PHP/Python/.NET/Ruby/YAML gadgets
CSRF	Auto-submit forms, JSON CSRF, SameSite bypass
Open Redirect	Protocol-relative, encoding chains, @ symbol tricks
Request Smuggling	CL.TE, TE.CL, HTTP/2 downgrade, TE obfuscation
Race Condition	TOCTOU, coupon reuse, rate limit bypass, double spend

---

Project Structure

claude-pentest-skills/
├── commands/
│   ├── scope.md            #   /scope — define target authorization
│   ├── recon.md            #   /recon — map attack surface
│   ├── hunt.md             #   /hunt — test vulnerability class
│   ├── validate.md         #   /validate — 6-gate quality check
│   ├── report.md           #   /report — generate pentest report
│   └── status.md           #   /status — engagement dashboard
│
├── agents/                 # Agent persona definitions
│   ├── recon-agent.md
│   ├── hunter-agent.md
│   └── validator-agent.md
│
├── skills/
│   ├── recon.md            #   Reconnaissance phases
│   ├── validate.md         #   6-gate validation process
│   ├── report.md           #   Report templates + CVSS guide
│   └── hunting/            #   Per-vuln-class methodology
│       ├── injection.md    │   auth-access.md  │  server-side.md
│       ├── client-side.md  │   session.md      │  business-logic.md
│       ├── config.md       │   ai-llm.md
│
├── payloads/               # Methodology + payload references
│   ├── sqli.md  │ xss.md  │ ssrf.md  │ ssti.md  │ xxe.md
│   ├── cmdi.md  │ idor.md │ jwt.md   │ oauth.md │ nosqli.md
│   ├── csrf.md  │ path-traversal.md   │ file-upload.md
│   ├── deserialization.md  │ open-redirect.md
│   ├── request-smuggling.md│ race-condition.md
│   └── prompt-injection.md
│
├── mcp/                    # MCP server integration docs
│   └── burp-suite/         #   Burp Suite proxy setup
│
├── tools/                  # Utilities
│   └── md2pdf.py           #   Markdown → styled PDF report
│
├── engagements/            # Per-target state (gitignored)
│   └── <target>/
│       ├── scope.md        │ findings.md    │ payload-log.md
│       ├── coverage.md     │ tech-stack.md  │ notes.md
│       └── report-*.md / report-*.pdf
│
├── local-payloads/         # Full curated payloads (gitignored)
├── CLAUDE.md               # Master config for Claude Code
└── .mcp.json.example       # MCP config template

---

Tool Integration

Tool	Integration	Use
Burp Suite	MCP server	Proxy, traffic analysis, request replay
SQLMap	Bash (post-detection)	Automated SQL injection exploitation
Commix	Bash (post-detection)	Automated command injection exploitation
Custom scripts	Claude generates on the fly	Race conditions, token analysis, encoding
md2pdf.py	Python (weasyprint)	Convert report markdown to styled PDF

SQLMap and Commix are used only after manual detection confirms the vulnerability. Never as first-pass scanners.

---

Local Payloads

The public payloads/ directory contains methodology and payload references. For curated payload lists with full exploit code, add them to local-payloads/ (gitignored):

mkdir local-payloads
# Add your curated .md files with full payloads here
# The hunt skills will reference both payloads/ and local-payloads/

---

Safety Rules

These are enforced in CLAUDE.md. Non-negotiable.

 1. SCOPE FIRST         /scope must run before any other command
 2. CHECK EVERY REQUEST verify against scope.md before sending
 3. LOG BEFORE ANALYZE  write payload to log BEFORE reading response
 4. NO OUT-OF-SCOPE     refuse requests to excluded domains/paths
 5. ASK IF UNCERTAIN    stop and confirm with user when scope is ambiguous
 6. WARN ON DESTRUCTIVE get explicit approval for DELETE/data modification

---

For authorized security testing only. Only test systems you own or have explicit written permission to test.