mcp-unreal: Agent for Claude Code

.claude/agents/security-reviwer.md

security-reviewer is an agent for Claude Code from remiphilippe/mcp-unreal. It costs 30 tokens per session (228 once invoked), scanned A, original, Apache-2.0.

A security review guide for open-source MCP servers. It checks for common problems involving file paths, command execution, credentials, logging, subprocesses, and dependencies.

In plain words
What is it for?
Use it before submitting a pull request or releasing an MCP server, with a pass-or-fail report and file-and-line references for each finding.
Why use it?
It helps find issues that could let users access unintended files, run unsafe commands, expose secrets, corrupt tool communication, or use vulnerable libraries.

Agent for Claude Code

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

This is remiphilippe/mcp-unreal's own configuration. It tells Claude Code how to work on mcp-unreal 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 mcp-unreal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to remiphilippe/mcp-unreal. 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/remiphilippe/mcp-unreal/main/.claude/agents/security-reviwer.md
Clone the repo
git clone --depth 1 https://github.com/remiphilippe/mcp-unreal

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/remiphilippe/mcp-unreal/security-reviwer/github.svg)](https://agentmods.dev/agents/remiphilippe/mcp-unreal/security-reviwer)
Your own site
<a href="https://agentmods.dev/agents/remiphilippe/mcp-unreal/security-reviwer"><img src="https://agentmods.dev/badge/agents/remiphilippe/mcp-unreal/security-reviwer/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-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/remiphilippe/mcp-unreal/security-reviwer"><img src="https://agentmods.dev/badge/agents/remiphilippe/mcp-unreal/security-reviwer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 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 $0.00030 $0.00228
Opus 5 $0.00015 $0.00114
Sonnet 5 $0.00006 $0.00046
Haiku 4.5 $0.00003 $0.00023

Measured 9d ago against content hash 28426c0126a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-reviewer 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 9d 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-reviwer.md · 18 lines

What it actually says

You are a security auditor for an open source MCP server.

Check for these specific vulnerabilities:

  1. PATH TRAVERSAL: Any file path from user input must use filepath.Clean + prefix check
  2. STDOUT POLLUTION: Any write to os.Stdout outside MCP SDK corrupts JSON-RPC. Grep for fmt.Print, os.Stdout, log.Print (without slog)
  3. SHELL INJECTION: exec.Command must never use "sh -c". All args must be explicit arrays
  4. CREDENTIAL LEAKS: No hardcoded tokens, passwords, API keys. Check .env files aren't committed
  5. SUBPROCESS SAFETY: All exec.Command calls need context.WithTimeout
  6. DEPENDENCY AUDIT: Check go.mod for known vulnerable versions

Output a structured report with PASS/FAIL per category and specific file:line references.

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. 9d ago First seen · 18 lines · 30 tokens per session scan A 28426c0126a1

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository remiphilippe/mcp-unreal (69 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 228 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 2026-08-30.