security

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

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.

agentmods
npx agentmods add agents/florian-priegnitz/a-eyes/security
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.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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 $0.00038 $0.00402
Opus 5 $0.00019 $0.00201
Sonnet 5 $0.00008 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 4d ago against content hash 915a8c2de1a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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. 4d 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 4mo ago), licensed MIT. It adds 38 tokens to every session and 402 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.