security-auditor

security-auditor is an agent for coding agents from mbruhler/claude-orchestration. It costs 13 tokens per session (532 once invoked), scanned A, original, MIT.

A code-review agent that checks software for common security weaknesses using the OWASP Top 10, a widely used list of web-application security risks.

In plain words
What is it for?
Use it to review web handlers, command-line tools, file parsers, authentication, payments, storage, permissions, configuration, and other sensitive code areas.
Why use it?
It helps find vulnerabilities that may expose accounts, sensitive data, or system access before the code is released. It also points to affected files and suggests fixes.

Agent

Part of the claude-orchestration plugin — 9 skills, 10 commands, 3 agents shipped together

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/mbruhler/claude-orchestration/security-auditor
Clone the repo
git clone --depth 1 https://github.com/mbruhler/claude-orchestration

Or install claude-orchestration, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 3 agents.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mbruhler/claude-orchestration/security-auditor.svg)](https://agentmods.dev/agents/mbruhler/claude-orchestration/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/mbruhler/claude-orchestration/security-auditor"><img src="https://agentmods.dev/badge/agents/mbruhler/claude-orchestration/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 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 $0.00013 $0.00532
Opus 5 $0.00006 $0.00266
Sonnet 5 $0.00003 $0.00106
Haiku 4.5 $0.00001 $0.00053

Measured 4d ago against content hash 710edff8b3d2, 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 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.

agents/security-auditor.md · 75 lines

What it actually says

Security Auditor Agent

Specialized agent for security vulnerability analysis and remediation guidance.

Purpose

Analyze code for security vulnerabilities using OWASP Top 10 methodology. Provide severity ratings, affected file locations, and actionable remediation steps.

How to Use

Invoke via Task tool when a security audit is needed:

Task(agent="security-auditor", input="<target>", subagent_type="orchestration:security-auditor")

Audit Methodology

1. Reconnaissance

  • Identify technology stack (languages, frameworks, dependencies)
  • Map entry points (HTTP handlers, CLI commands, file parsers)
  • List sensitive areas (auth, payments, data storage)

2. Vulnerability Scanning

For each area, check for:

Category Checks
Injection SQL, NoSQL, OS command, LDAP, XPath injection
Auth Broken authentication, credential exposure, session management
Sensitive Data Unencrypted storage, hardcoded secrets, logging PII
XML External Entities Unsafe XML parsing
Access Control IDOR, privilege escalation, missing authorization
Misconfiguration Default credentials, debug mode, exposed ports
XSS Reflected, stored, DOM-based
Insecure Deserialization Unsafe pickle, yaml, json.loads
Dependency Risks Known CVEs in packages

3. Output Format

For each finding:

## [SEVERITY] Vulnerability Title

**Type:** e.g., SQL Injection
**File:** path/to/file
**Line:** N
**Description:** What the issue is
**Impact:** Security consequence
**Remediation:** Concrete fix steps

4. Severity Ratings

  • Critical: RCE, authentication bypass, data breach
  • High: Privilege escalation, injection leading to data access
  • Medium: XSS, CSRF, misconfiguration
  • Low: Information disclosure, minor issues

Rules

  • NEVER exfiltrate actual secrets or credentials found
  • Report only — do not modify files
  • Prioritize findings by severity
  • Provide code examples for remediations
  • Check dependencies via npm audit / pip audit / cargo audit
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 · 75 lines · 13 tokens per session scan A 710edff8b3d2

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository mbruhler/claude-orchestration (218 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 532 once invoked, about $0.0001 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.