A form-testing tool that submits unusual input values to look for security and validation problems. Its checks include cross-site scripting (XSS), SQL injection, Unicode handling, and length limits.

Use it during security and pre-release testing of text, email, password, search, and other form fields. It can test selected categories or all 41 listed test inputs.

Normal test values may not reveal unsafe input handling or incorrectly enforced limits. It exposes how forms respond to potentially harmful or difficult-to-process data.

form-fuzzer — Skill for Claude Code by ncklrs

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ncklrs/claude-chrome-user-testing --skill form-fuzzer

Clone the repo

git clone --depth 1 https://github.com/ncklrs/claude-chrome-user-testing

Made for: Claude Code.

Or install user-testing-agent, the plugin that ships this one along with the rest of its 14 skills, 10 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ncklrs/claude-chrome-user-testing/form-fuzzer/github.svg)](https://agentmods.dev/skills/ncklrs/claude-chrome-user-testing/form-fuzzer)

Your own site

<a href="https://agentmods.dev/skills/ncklrs/claude-chrome-user-testing/form-fuzzer"><img src="https://agentmods.dev/badge/skills/ncklrs/claude-chrome-user-testing/form-fuzzer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ncklrs/claude-chrome-user-testing/form-fuzzer"><img src="https://agentmods.dev/badge/skills/ncklrs/claude-chrome-user-testing/form-fuzzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,437 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01437
Opus 5	$0.00000	$0.00718
Sonnet 5	$0.00000	$0.00287
Haiku 4.5	$0.00000	$0.00144

Measured 10d ago against content hash 1ccfc3045fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

form-fuzzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/form-fuzzer/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Form Fuzzer Skill

Test form inputs with edge case payloads to find security vulnerabilities and encoding issues.

When to Use

Security testing forms for XSS/SQLi vulnerabilities
Testing input validation and sanitization
Finding unicode/encoding handling issues
Checking length limit enforcement
Pre-deployment security checks

Flags

--fuzz                           Enable fuzzing mode
--fuzz-category <category>       Category: xss | sqli | unicode | length | all (default: all)

Fuzzing Categories

Category	Purpose	Payload Count
`xss`	Test XSS sanitization	15 payloads
`sqli`	Test SQL injection prevention	12 payloads
`unicode`	Test encoding handling	10 payloads
`length`	Test length limits	4 payloads
`all`	All categories combined	41 payloads

Behavior

When --fuzz is active:

Discovery: Find all form inputs on the page
Classification: Identify input types (text, email, password, search, etc.)
Injection: For each input, try payloads from selected category
Observation: Check response for each payload:
- Sanitized: Payload escaped/stripped (PASS)
- Rejected: Clear error message (PASS)
- Executed: XSS/SQLi worked (CRITICAL)
- Error: Application error/crash (MAJOR)
- Stored: Payload persists in DOM (CRITICAL)
Reporting: Generate security-focused report section

Response Classification

XSS Detection

// Check if script executed
// Check if payload appears unescaped in DOM
// Check for alert/console activity
// Check if event handlers fire

SQL Injection Detection

// Check for database error messages
// Check for unusual response time (time-based)
// Check for data leakage
// Check for error 500 responses

Encoding Issues

// Check for garbled text
// Check for broken layout (RTL markers)
// Check for missing characters
// Check for incorrect rendering

Read the full file on GitHub · 200 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

payloads.json 9.0 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 200 lines · 0 tokens per session scan A 1ccfc3045fbf

Subscribe to this mod's changes

form-fuzzer is a skill published in the GitHub repository ncklrs/claude-chrome-user-testing (20 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,437 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Security Testing accessibility chrome-automation personas usability

testing-e2e

End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.

yonatangross/orchestkit · 55 tokens

form-fuzzer