xss-attacker

xss-attacker is an agent for Claude Code from morodomi/redteam-skills. It costs 34 tokens per session (1,360 once invoked), scanned A, original, MIT.

A static-analysis agent for finding cross-site scripting (XSS), a vulnerability that lets untrusted input run as code in a user's browser. It checks reflected, DOM-based, and stored XSS patterns in several web frameworks.

In plain words
What is it for?
Scanning PHP, Laravel, Django, Flask, and Node.js code for risky output patterns, dangerous DOM operations, and missing input escaping.
Why use it?
It highlights unsafe output and missing sanitization before malicious input can affect users.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the redteam-core plugin — 4 skills, 18 agents shipped together

Good fit Scanning PHP, Laravel, Django, Flask, and Node.js code for risky output patterns, dangerous DOM operations, and missing input escaping.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/morodomi/redteam-skills/xss-attacker
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.

Clone the repo
git clone --depth 1 https://github.com/morodomi/redteam-skills

Made for: Claude Code.

Or install redteam-core, the plugin that ships this one along with the rest of its 4 skills, 18 agents.

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.

agentmods badge for xss-attacker

README.md
[![agentmods](https://agentmods.dev/badge/agents/morodomi/redteam-skills/xss-attacker/github.svg)](https://agentmods.dev/agents/morodomi/redteam-skills/xss-attacker)
Your own site
<a href="https://agentmods.dev/agents/morodomi/redteam-skills/xss-attacker"><img src="https://agentmods.dev/badge/agents/morodomi/redteam-skills/xss-attacker/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.

agentmods 80×15 button for xss-attacker

Your own site · 80×15
<a href="https://agentmods.dev/agents/morodomi/redteam-skills/xss-attacker"><img src="https://agentmods.dev/badge/agents/morodomi/redteam-skills/xss-attacker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,360 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01360
Opus 5 $0.00017 $0.00680
Sonnet 5 $0.00007 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 8d ago against content hash c013e34d753b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

xss-attacker 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 8d 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.

plugins/redteam-core/agents/xss-attacker.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XSS Attacker

Reflected XSS、DOM XSS、Stored XSS脆弱性を静的解析で検出するエージェント。

Detection Targets

Type Description Pattern
Reflected XSS ユーザー入力の直接出力 エスケープなしのecho/print
DOM XSS クライアントサイドでのDOM操作 innerHTML, document.write等
Stored XSS DB保存後の出力 保存→取得→エスケープなし出力
Sanitization Missing サニタイズ不備 htmlspecialchars等の欠如

Framework Detection Patterns

Framework Vulnerable Pattern Safe Pattern
Laravel {!! $input !!}, echo $input {{ $input }}, e($input)
Django |safe, mark_safe() 自動エスケープ(デフォルト)
Flask |safe, Markup() 自動エスケープ(Jinja2)
Express res.send(input), innerHTML= テンプレートエンジン使用

Dangerous Patterns

patterns:
  # PHP/Laravel
  - 'echo\s+\$'
  - 'print\s+\$'
  - '\{\!\!\s*\$.*\!\!\}'
  - '->with\s*\([^)]*\$_'

  # Python/Django/Flask
  - '\|safe'
  - 'mark_safe\s*\('
  - 'Markup\s*\('

  # Node.js/Express
  - 'res\.send\s*\([^)]*\+'
  - 'innerHTML\s*='
  - 'document\.write\s*\('

DOM XSS Dangerous Patterns

Category Sink Pattern
DOM操作 innerHTML \.innerHTML\s*=
DOM操作 outerHTML \.outerHTML\s*=
DOM操作 document.write document\.write\s*\(
実行系 eval eval\s*\(.*location
jQuery html() \.html\s*\(
jQuery append() \.append\s*\(

Sources(トレース対象):

  • location.hash, location.search
  • document.URL, document.referrer
  • window.name

Stored XSS Detection Patterns

Framework Save Pattern Display Pattern
Laravel ->create($request->all()) {!! $model->field !!}
Django .objects.create(**request.POST) {{ field|safe }}
Express collection.insertOne(req.body) innerHTML = data.field

NOTE: 静的解析の限界上、保存と表示の紐付けは同一モデル/変数名での推定。

Output Format

{
  "metadata": {
    "scan_id": "<uuid>",
    "scanned_at": "<timestamp>",
    "agent": "xss-attacker"
  },
  "vulnerabilities": [
    {
      "id": "XSS-001",
      "type": "reflected",
      "vulnerability_class": "xss",
      "cwe_id": "CWE-79",
      "severity": "high",
      "file": "resources/views/user.blade.php",
      "line": 23,
      "code": "{!! $request->input('name') !!}",
      "description": "User input rendered without escaping",
      "remediation": "Use {{ }} instead of {!! !!} for auto-escaping"
    },
    {
      "id": "XSS-002",
      "type": "dom",
      "vulnerability_class": "xss",
      "cwe_id": "CWE-79",
      "severity": "high",
      "file": "public/js/app.js",
      "line": 45,
      "code": "element.innerHTML = location.hash.slice(1)",
      "description": "DOM XSS via location.hash to innerHTML",
      "remediation": "Use textContent or sanitize input before innerHTML"
    },
    {
      "id": "XSS-003",
      "type": "stored",
      "vulnerability_class": "xss",
      "cwe_id": "CWE-79",
      "severity": "critical",
      "file": "resources/views/comments.blade.php",
      "line": 12,
      "code": "{!! $comment->body !!}",
      "description": "Stored XSS via unescaped database content",
      "remediation": "Use {{ }} for auto-escaping or sanitize on save"
    }
  ],
  "summary": {
    "total": 3,
    "critical": 1,
    "high": 2,
    "medium": 0,
    "low": 0
  }
}

Read the full file on GitHub · 158 lines

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.

  1. 8d ago First seen · 158 lines · 34 tokens per session scan A c013e34d753b

Subscribe to this mod's changes

xss-attacker is an agent published in the GitHub repository morodomi/redteam-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,360 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other agents, from other repositories

cheatsheet-duplication-checker

Duplication and placement reviewer for OWASP cheat sheet changes. Checks whether added content repeats material already in the series and whether it belongs in the cheat sheet being edited. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 52 tokens

cheatsheet-link-auditor

Link and source-quality auditor for OWASP cheat sheet changes. Goes beyond "does the link work" to judge whether each cited page is authoritative and actually supports the claim it is attached to. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 56 tokens

cheatsheet-security-reviewer

Security-correctness reviewer for OWASP cheat sheet changes. Use to verify that the security advice in a diff is technically correct, current, and not dangerous. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 49 tokens

cheatsheet-language-reviewer

Language and editorial reviewer for OWASP cheat sheet changes. Checks US English correctness, grammar, clarity for non-native readers, and the project's structural/style conventions. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 48 tokens

cheatsheet-practicality-reviewer

Developer-practicality reviewer for OWASP cheat sheet changes. Use to judge whether the advice is actionable, realistic, and useful to a working developer. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 49 tokens

threat-modeler

Use this agent when the user asks to "create a threat model", "analyze threats", "STRIDE analysis", "what are the threats", "threat modeling", "identify attack vectors", "map attack surface", or needs systematic threat identification with data flow diagrams.

allsmog/vuln-scout · 60 tokens