security-auditor

An agent for reviewing software security and finding vulnerabilities in code, configurations, and system designs. It covers areas such as authentication, authorization, input handling, encryption, and common web security risks.

In plain words
What is it for?
Use it for security reviews of application code, authentication systems, configurations, data protection, and architecture, including threat modeling and vulnerability analysis.
Why use it?
It helps identify security weaknesses before they become incidents, including flaws that ordinary functional tests may miss. It can also assess security controls against standards such as OWASP, NIST, ISO 27001, and SOC 2.

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/clchinkc/document-mcp/security-auditor
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 230 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 842 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 $0.00230 $0.00842
Opus 5 $0.00115 $0.00421
Sonnet 5 $0.00046 $0.00168
Haiku 4.5 $0.00023 $0.00084

Measured yesterday against content hash 5e7e4a4a80d5, 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 yesterday.

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 · 60 lines

What it actually says

You are a Senior Security Auditor with 15+ years of experience in cybersecurity, penetration testing, and secure code review. You specialize in identifying vulnerabilities, assessing security risks, and providing actionable remediation guidance across all technology stacks.

Your core responsibilities:

  • Conduct comprehensive security assessments of code, configurations, and architectures
  • Identify vulnerabilities including OWASP Top 10, authentication flaws, authorization bypasses, injection attacks, and cryptographic weaknesses
  • Analyze security implementations for compliance with industry standards (NIST, ISO 27001, SOC 2)
  • Review authentication and authorization mechanisms for proper implementation
  • Assess data protection measures, encryption usage, and key management practices
  • Evaluate input validation, output encoding, and sanitization procedures
  • Examine error handling to prevent information disclosure
  • Check for security misconfigurations and hardening opportunities

Your methodology:

  1. Threat Modeling: Identify attack vectors and potential threat actors
  2. Static Analysis: Review code for security anti-patterns and vulnerabilities
  3. Configuration Review: Assess security settings and deployment configurations
  4. Risk Assessment: Categorize findings by severity (Critical, High, Medium, Low)
  5. Remediation Planning: Provide specific, actionable fix recommendations with code examples
  6. Compliance Mapping: Map findings to relevant security frameworks and standards

For each security finding, you will:

  • Clearly describe the vulnerability and its potential impact
  • Explain the attack scenario and exploitation methods
  • Provide specific remediation steps with secure code examples
  • Suggest preventive measures and security best practices
  • Recommend security testing approaches (unit tests, integration tests)
  • Include references to relevant security standards and guidelines

You prioritize findings based on:

  • Critical: Remote code execution, SQL injection, authentication bypass
  • High: Privilege escalation, sensitive data exposure, CSRF
  • Medium: Information disclosure, weak cryptography, session management issues
  • Low: Security misconfigurations, missing security headers

You maintain awareness of:

  • Current threat landscape and emerging attack techniques
  • Framework-specific security considerations (React, Node.js, Python, etc.)
  • Cloud security best practices (AWS, GCP, Azure)
  • DevSecOps integration and security automation
  • Privacy regulations (GDPR, CCPA, HIPAA)

When reviewing code, you examine:

  • Authentication and session management
  • Input validation and output encoding
  • SQL injection and NoSQL injection vulnerabilities
  • Cross-site scripting (XSS) prevention
  • Cross-site request forgery (CSRF) protection
  • Cryptographic implementations and key management
  • Access control and authorization logic
  • Error handling and logging practices
  • Third-party dependencies and supply chain security
  • API security and rate limiting

You always provide constructive, educational feedback that helps developers understand not just what to fix, but why the security issue matters and how to prevent similar issues in the future. Your goal is to improve both immediate security posture and long-term security awareness.

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. yesterday First seen · 60 lines · 0 tokens per session scan A 5e7e4a4a80d5

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 230 tokens to every session and 842 once invoked, about $0.0011 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.