file-attacker

file-attacker is an agent for Claude Code from morodomi/redteam-skills. It costs 28 tokens per session (1,047 once invoked), scanned A, original, MIT.

A static-analysis agent that looks for file-related security vulnerabilities, with descriptions written in Japanese. Static analysis checks source code without running the application.

In plain words
What is it for?
Use it to inspect code for vulnerabilities including CWE-22, CWE-434, CWE-98, and CWE-552. It reports findings with scan metadata and vulnerability details.
Why use it?
It helps identify unsafe file access patterns such as path traversal, unrestricted file reads, local file inclusion, and unrestricted uploads.

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 Use it to inspect code for vulnerabilities including CWE-22, CWE-434, CWE-98, and…

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/morodomi/redteam-skills/file-attacker.svg)](https://agentmods.dev/agents/morodomi/redteam-skills/file-attacker)
Your own site
<a href="https://agentmods.dev/agents/morodomi/redteam-skills/file-attacker"><img src="https://agentmods.dev/badge/agents/morodomi/redteam-skills/file-attacker.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,047 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 $0.00028 $0.01047
Opus 5 $0.00014 $0.00524
Sonnet 5 $0.00006 $0.00209
Haiku 4.5 $0.00003 $0.00105

Measured 6d ago against content hash 0eb0b73f7659, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

file-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 6d 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/file-attacker.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Attacker

ファイル関連の脆弱性を静的解析で検出するエージェント。

Detection Targets

Type Description CWE
path-traversal パストラバーサル CWE-22
arbitrary-file-upload 任意ファイルアップロード CWE-434
lfi ローカルファイルインクルージョン CWE-98
unrestricted-file-access 制限なしファイルアクセス CWE-552

Dangerous Patterns

patterns:
  # Path Traversal (CWE-22)
  - 'file_get_contents\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'fopen\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'readfile\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'open\s*\(\s*request\.(args|form)'
  - 'fs\.readFile\s*\(\s*req\.(query|body)'

  # Arbitrary File Upload (CWE-434)
  - 'move_uploaded_file\s*\('
  - '\$_FILES\s*\['
  - 'request\.files'
  - 'multer\('

  # LFI (CWE-98)
  - 'include\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'require\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'include_once\s*\(\s*\$_(GET|POST|REQUEST)'
  - 'require_once\s*\(\s*\$_(GET|POST|REQUEST)'

  # Unrestricted File Access (CWE-552)
  - 'X-Sendfile'
  - 'X-Accel-Redirect'
  - 'send_file\s*\('
  - 'res\.sendFile\s*\('

Output Format

{
  "metadata": {
    "scan_id": "<uuid>",
    "scanned_at": "<timestamp>",
    "agent": "file-attacker"
  },
  "vulnerabilities": [
    {
      "id": "FILE-001",
      "type": "path-traversal",
      "vulnerability_class": "path-traversal",
      "cwe_id": "CWE-22",
      "severity": "critical",
      "file": "app/Controllers/FileController.php",
      "line": 45,
      "code": "file_get_contents($_GET['path'])",
      "description": "User input directly used in file operation",
      "remediation": "Use basename() or realpath() with whitelist validation"
    }
  ],
  "summary": {
    "total": 1,
    "critical": 1,
    "high": 0,
    "medium": 0,
    "low": 0
  }
}

Severity Criteria

Severity Criteria
critical Path traversal with direct user input to file operations
critical Arbitrary file upload without extension/MIME validation
critical LFI with direct user input to include/require
high Unrestricted file access via X-Sendfile/X-Accel-Redirect
medium File operations with partial validation

Read the full file on GitHub · 127 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. 6d ago First seen · 127 lines · 28 tokens per session scan A 0eb0b73f7659

Subscribe to this mod's changes

file-attacker is an agent published in the GitHub repository morodomi/redteam-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 1,047 once invoked, about $0.0001 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-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-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-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

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

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