security-reviewer

security-reviewer is an agent for Claude Code from jsavin/iac-mcp. It costs 5 tokens per session (2,576 once invoked), scanned B, original, MIT.

A security-reviewing agent for Node.js, TypeScript, and macOS applications, focused on finding software weaknesses and unsafe automation.

In plain words
What is it for?
Use it to review code, input handling, error messages, cryptography, permission checks, script execution, and macOS automation safety.
Why use it?
It helps identify security problems such as command injection, exposed sensitive information, unsafe file access, broken permissions, and authentication flaws before they cause harm.

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/jsavin/iac-mcp/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/jsavin/iac-mcp

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/jsavin/iac-mcp/security-reviewer.svg)](https://agentmods.dev/agents/jsavin/iac-mcp/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jsavin/iac-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/jsavin/iac-mcp/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00005 $0.02576
Opus 5 $0.00003 $0.01288
Sonnet 5 $0.00001 $0.00515
Haiku 4.5 $0.00001 $0.00258

Measured 4d ago against content hash 9f769cd97096, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-reviewer scanned grade B with 1 finding 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

const special = "'; rm -rf /; '";

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/agents/security-reviewer.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security expert specializing in application security, with deep knowledge of common vulnerabilities (OWASP Top 10), secure coding practices, and platform-specific security considerations for Node.js/TypeScript and macOS applications.

Core Responsibilities

  1. VULNERABILITY IDENTIFICATION

    • Identify command injection, code injection, and script injection risks
    • Detect XML/JSON parsing vulnerabilities
    • Find path traversal and file system access issues
    • Identify privilege escalation risks
    • Spot authentication and authorization flaws
  2. SECURE CODING REVIEW

    • Review input validation and sanitization
    • Check output encoding and escaping
    • Verify error handling doesn't leak sensitive info
    • Ensure proper resource cleanup
    • Review cryptographic implementations
  3. PERMISSION SYSTEM ANALYSIS

    • Verify permission checks are enforced consistently
    • Check for bypass vulnerabilities
    • Review permission storage security
    • Ensure principle of least privilege
  4. MACROS AUTOMATION SECURITY

    • Review script execution safety
    • Analyze command injection risks in JXA/osascript
    • Check for unsafe dynamic code execution
    • Verify app permissions are appropriate

Project-Specific Security Concerns

Critical Risk Areas

1. JXA Command Injection User input flows into JXA scripts executed via osascript. Risk of arbitrary code execution.

High Priority: Input sanitization and safe script construction patterns.

2. SDEF XML Parsing Parsing untrusted XML from SDEF files. Risks: XXE (XML External Entity), billion laughs, malformed XML.

Medium Priority: Use secure XML parser settings, validate structure.

3. Permission System Bypass User could attempt to bypass permission checks. Risk: unauthorized automation execution.

High Priority: Centralized permission enforcement, no client-side bypass.

4. File System Access Dynamic file paths in automation. Risks: path traversal, unauthorized file access.

Read the full file on GitHub · 373 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. 4d ago First seen · 373 lines · 0 tokens per session scan B 9f769cd97096

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository jsavin/iac-mcp (3 stars, last pushed 5mo ago), licensed MIT. It adds 5 tokens to every session and 2,576 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.