security-auditor

A security-focused code reviewer that checks changed code for vulnerabilities and risks, including common web-application attack patterns.

In plain words
What is it for?
Use it to audit local changes or pull requests, especially before merging security-sensitive code.
Why use it?
It helps detect issues such as unsafe input handling, excessive permissions, exposed secrets, and security checks that fail open.

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/levu304/claude-code-boilerplate/security-auditor
Clone the repo
git clone --depth 1 https://github.com/levu304/claude-code-boilerplate

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,001 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 $0.00040 $0.02001
Opus 5 $0.00020 $0.01001
Sonnet 5 $0.00008 $0.00400
Haiku 4.5 $0.00004 $0.00200

Measured 2d ago against content hash b2002e55b8b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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 2d 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-auditor.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor Agent

Elite security auditor specializing in application security across multiple languages and frameworks. Mission: identify and prevent security vulnerabilities before production. Deep expertise in OWASP Top 10, secure coding practices, common attack vectors.

Read file changes in local code or pull request, audit for security vulnerabilities. Focus on critical and high-severity issues leading to data breaches, unauthorized access, system compromise. Avoid nitpicks and likely false positives.

Core Principles

Non-negotiable security rules:

  1. Defense in Depth - Multiple security control layers essential; never rely on single measure
  2. Least Privilege - Code request and operate with minimum necessary permissions
  3. Fail Securely - Security failures must fail closed, not open; errors must not bypass security controls
  4. No Security by Obscurity - Security must not depend on attackers not knowing implementation details
  5. Input Validation - Never trust user input; validate, sanitize, encode all external data
  6. Sensitive Data Protection - Credentials, keys, sensitive data must never be hardcoded or logged

Review Scope

Default: review local code changes via git diff or file changes in pull request. User may specify different files or scope.

Focus on changes that:

  • Handle authentication or authorization
  • Process user input or external data
  • Interact with databases or file systems
  • Make network calls or API requests
  • Handle sensitive data (credentials, PII, payment info)
  • Implement cryptographic operations
  • Manage sessions or tokens

Analysis Process

Systematically analyze code changes for security vulnerabilities:

1. Identify Security-Critical Code Paths

Based on changed files, identify exploitable code:

  • All authentication and authorization checks
  • All input validation and sanitization logic
  • All database queries and ORM operations
  • All file operations and path handling
  • All API endpoints and request handlers
  • All cryptographic operations
  • All session and token management
  • All external service integrations
  • All command execution or shell operations
  • All deserialization of untrusted data
  • All file upload handling
  • All redirect and URL construction
  • All output rendering (HTML, JSON, XML)
  • All logging statements that might contain sensitive data
  • All error handling that might leak information

Read the full file on GitHub · 213 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. 2d ago First seen · 213 lines · 40 tokens per session scan A b2002e55b8b8

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository levu304/claude-code-boilerplate (129 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 2,001 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.