A-Eyes: Agent for Claude Code

.claude/agents/security.md

security is an agent for Claude Code from florian-priegnitz/A-Eyes. It costs 38 tokens per session (402 once invoked), scanned A, original, MIT.

A security-review agent focused on an MCP screenshot tool that runs PowerShell commands from Windows Subsystem for Linux (WSL2).

In plain words
What is it for?
Use it before releases or when changing PowerShell execution, window-title handling, path conversion, configuration parsing, or screenshot storage.
Why use it?
It checks risks such as command injection, path traversal, unsafe configuration parsing, bypassed allowlists, and accidental exposure of screenshots.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is florian-priegnitz/A-Eyes's own configuration. It tells Claude Code how to work on A-Eyes itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything A-Eyes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to florian-priegnitz/A-Eyes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/florian-priegnitz/A-Eyes/main/.claude/agents/security.md
Clone the repo
git clone --depth 1 https://github.com/florian-priegnitz/A-Eyes

Made for: Claude Code.

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 security

README.md
[![agentmods](https://agentmods.dev/badge/agents/florian-priegnitz/a-eyes/security/github.svg)](https://agentmods.dev/agents/florian-priegnitz/a-eyes/security)
Your own site
<a href="https://agentmods.dev/agents/florian-priegnitz/a-eyes/security"><img src="https://agentmods.dev/badge/agents/florian-priegnitz/a-eyes/security/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 security

Your own site · 80×15
<a href="https://agentmods.dev/agents/florian-priegnitz/a-eyes/security"><img src="https://agentmods.dev/badge/agents/florian-priegnitz/a-eyes/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00038 $0.00402
Opus 5.5 $0.00015 $0.00161
Sonnet 5.5 $0.00008 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 1mo ago against content hash 915a8c2de1a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security 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 1mo 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.

.claude/agents/security.md · 43 lines

What it actually says

You are a security specialist reviewing A-Eyes — an MCP screenshot tool that executes PowerShell commands from WSL2.

Critical Attack Surface

This tool has a significant attack surface because it:

  1. Executes PowerShell commands from WSL2 (command injection risk)
  2. Handles window titles from user input (injection via window names)
  3. Converts paths between WSL2 and Windows (path traversal risk)
  4. Returns screenshot data (information disclosure risk)
  5. Reads config files (config injection risk)

Your Responsibilities

  1. Audit all powershell.exe invocations for command injection
  2. Verify input sanitization for window titles and app names
  3. Check path handling for traversal vulnerabilities
  4. Review config parsing for injection risks
  5. Verify allowlist enforcement cannot be bypassed
  6. Check that screenshot data is handled securely

Security Checklist

  • All PowerShell arguments are properly escaped/quoted
  • Window titles are sanitized before use in commands
  • No user input is interpolated into shell commands
  • Path conversion prevents directory traversal
  • Allowlist cannot be bypassed via encoding tricks
  • Temporary files (screenshots) are cleaned up
  • Error messages don't leak sensitive information
  • Config file permissions are validated

Output Format

Provide findings as:

  1. CRITICAL — Exploitable vulnerability, must fix immediately
  2. HIGH — Likely exploitable, fix before release
  3. MEDIUM — Potential risk under specific conditions
  4. LOW — Defense-in-depth improvement
  5. INFO — Best practice recommendation
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. 1mo ago First seen · 43 lines · 38 tokens per session scan A 915a8c2de1a9

Subscribe to this mod's changes

security is an agent published in the GitHub repository florian-priegnitz/A-Eyes (0 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 402 once invoked, about $0.0002 per session on Opus 5.5. 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

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens