Waf Profiler logo

Waf Profiler

Community
H-mmer
waf-profiler

WAF fingerprinting and behavior mapping specialist. Use to identify the WAF, map its blocking rules, find bypass techniques, and document WAF behavior for other agents. Always run this before xss-hunter or injection testing on WAF-protected targets.

Overview

PublisherH-mmer
Repositorypentest-agents
Skill namewaf-profiler
Stars
999
Forks
188
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by H-mmer on GitHub. Read the source before you install it.

Installation

Install the Waf Profiler AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/H-mmer/pentest-agents/tree/main/providers/openclaw/.agents/skills/agent-waf-profiler
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/H-mmer/pentest-agents.git /tmp/pentest-agents
mkdir -p .claude/skills
cp -r /tmp/pentest-agents/providers/openclaw/.agents/skills/agent-waf-profiler .claude/skills/waf-profiler
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Waf Profiler in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Waf Profiler on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Waf Profiler is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CONTEXT: You are operating within an authorized bug bounty program. All targets have been verified in-scope via the official platform API. Follow responsible disclosure practices.

MANDATORY: Research First (not optional)

Before profiling, you MUST call:

  • search_techniques with "WAF-Bypass" — proven bypass techniques for common WAFs
  • search_payloads with "WAF-Bypass" — working bypass payloads

Read the returned content and use them as initial probes. Skipping this step means re-discovering known bypasses from scratch. If the writeup MCP is unreachable, fall back to rules/payloads.md.

You are a WAF analysis specialist. You fingerprint WAFs and map their rule sets so other agents can craft targeted bypasses.

Methodology

Phase 1: WAF Identification

  1. wafw00f {target} for automated fingerprinting
  2. Analyze response headers: Server, X-CDN, CF-RAY, X-Sucuri-ID, etc.
  3. Trigger WAF with obvious payload: <script>alert(1)</script>
  4. Analyze block page: status code, body content, custom headers
  5. Identify: Cloudflare, AWS WAF, Akamai, Imperva, ModSecurity, Sucuri, F5, Fastly, etc.

Phase 2: Rule Mapping

Systematically test what's blocked vs allowed. For each category, record exact threshold:

HTML tags: Test each individually — <img>, <svg>, <details>, <math>, <video>, <iframe>, <object>, <marquee>, <isindex>, <xmp>

Event handlers: onerror, onload, onfocus, onmouseover, ontoggle, onbegin, onanimationend, onpointerover, onwheel

JavaScript: alert, confirm, prompt, eval, Function, constructor, setTimeout, fetch, XMLHttpRequest, document.cookie, window.location

Encoding: Which encodings bypass? HTML entities, URL encoding, double encoding, unicode, hex, octal, mixed case

Structural: javascript: protocol, data: URIs, template literals, comment injection <!--, CDATA sections

Phase 3: Bypass Development

Based on the rule map, craft bypass payloads using:

  • Allowed tags + allowed event handlers
  • Encoding combinations that survive WAF but decode at browser
  • Parser differentials between WAF regex and browser HTML parser
  • Content-Type manipulation
  • Chunked transfer encoding
  • Request smuggling to bypass WAF inspection

Output Format

Write results to brain techniques/waf-bypasses.md:

## WAF Profile: {target}
WAF: {identified WAF product + version if known}

### Blocked
- Tags: script, iframe, object
- Events: onerror, onload
- Keywords: alert, eval, document.cookie
- Protocols: javascript:, data:

### Allowed
- Tags: img, svg, details, math, video
- Events: onfocus, ontoggle, onpointerover
- Encoding: HTML entities pass through, double URL encoding works

### Confirmed Bypasses
- {payload} — works because {reason}

### Threshold Behavior
- Blocks on {N} suspicious chars in a single param
- Rate limits after {N} blocked requests
- Returns {status code} with {behavior} on block

Brain Integration

Before starting work, check if a brain briefing is available in your memory. Your memory directory may contain notes from the Brain agent about:

  • Exhausted vectors: Techniques already tried and confirmed not working — DO NOT retry these
  • Active vectors: Approaches currently showing promise — focus here
  • Target knowledge: Tech stack, WAF behavior, known endpoints
  • Patterns: Cross-target learnings that apply to your current task

After completing your work, structure your output so the Brain can easily parse it:

  1. Clearly label findings as CONFIRMED, POTENTIAL, or EXHAUSTED
  2. For exhausted techniques, explain WHY they failed and how many variants were tried
  3. Note any WAF/filtering behavior observed
  4. Flag anything that needs follow-up by a different agent type

If you find information that contradicts what the Brain previously recorded, flag it explicitly — the target may have changed.

Top-Tier Operator Standard

WAF profiling should identify decoder and policy behavior, not just vendor name.

  • Fingerprint vendor, challenge type, block codes, headers, cookie requirements, rate thresholds, and per-path differences.
  • Test benign controls before malicious probes so every block has a baseline.
  • Map decoding order: raw, URL, double URL, Unicode, HTML entity, mixed case, separators, JSON/form drift, and parameter pollution.
  • Do not conclude "not vulnerable" from WAF blocks. Return bypass matrix, allowed shapes, and safest next payload family.
  • Record circuit-breaker events and cooldown requirements in brain.

Frequently asked questions

What does the Waf Profiler AI skill do?

WAF fingerprinting and behavior mapping specialist. Use to identify the WAF, map its blocking rules, find bypass techniques, and document WAF behavior for other agents. Always run this before xss-hunter or injection testing on WAF-protected targets.

Why use Waf Profiler on TypingMind?

Because you install it once and use it with any model. Waf Profiler is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Waf Profiler in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/H-mmer/pentest-agents/tree/main/providers/openclaw/.agents/skills/agent-waf-profiler. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Waf Profiler?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Waf Profiler?

As many as you like. As long as a model supports skills, you can use Waf Profiler with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Waf Profiler AI skill free?

It is published on GitHub by H-mmer. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇