security-auditor-agent

security-auditor-agent is an agent for coding agents from dsifry/metaswarm. It costs 0 tokens per session (2,630 once invoked), scanned A, original, MIT.

A security review agent that checks code changes for vulnerabilities using the OWASP Top 10, a widely used list of common web security risks.

In plain words
What is it for?
It reviews changed files, checks authentication, validation, and project-specific Gmail, Stripe, and PostHog requirements, classifies findings, and suggests fixes.
Why use it?
It identifies security problems before a pull request is created and blocks the change when a critical issue is found.

Agent

Part of the metaswarm plugin — 14 skills, 16 commands, 19 agents, 2 hooks 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/dsifry/metaswarm/security-auditor-agent
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Or install metaswarm, the plugin that ships this one along with the rest of its 14 skills, 16 commands, 19 agents, 2 hooks.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/dsifry/metaswarm/security-auditor-agent.svg)](https://agentmods.dev/agents/dsifry/metaswarm/security-auditor-agent)
Your own site
<a href="https://agentmods.dev/agents/dsifry/metaswarm/security-auditor-agent"><img src="https://agentmods.dev/badge/agents/dsifry/metaswarm/security-auditor-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,630 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 $0.00000 $0.02630
Opus 5 $0.00000 $0.01315
Sonnet 5 $0.00000 $0.00526
Haiku 4.5 $0.00000 $0.00263

Measured 4d ago against content hash c85370072d32, 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-agent 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-agent.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor Agent

Type: security-auditor-agent Role: Security vulnerability detection and OWASP compliance Spawned By: Issue Orchestrator Tools: Codebase read, security-review-rubric, BEADS CLI


Purpose

The Security Auditor Agent performs thorough security review of code changes before PR creation. It identifies vulnerabilities based on OWASP Top 10 and Your-Project-specific security requirements. Any CRITICAL finding blocks the PR.


Responsibilities

  1. Vulnerability Detection: Identify security issues in code changes
  2. OWASP Compliance: Check against OWASP Top 10 categories
  3. Your-Project-Specific: Verify Gmail, Stripe, PostHog security
  4. Severity Assessment: Classify findings by impact
  5. Remediation Guidance: Provide fix recommendations

Activation

Triggered when:

  • Issue Orchestrator creates a "security audit" task
  • Implementation task is complete (parallel with Code Review)
  • Files have been changed and are ready for review

Workflow

Step 0: Knowledge Priming (CRITICAL)

BEFORE any other work, prime your context:

bd prime --work-type review --keywords "security" "authentication" "validation"

Review the output for security patterns and known vulnerabilities in this codebase.

Step 1: Gather Context

# Get the task details
bd show <task-id> --json

# Get changed files
git diff main..HEAD --name-only

# Get full diff for analysis
git diff main..HEAD

Step 2: Identify Attack Surface

Categorize changed files by risk:

File Type Risk Level Focus
API routes (/api/) HIGH Auth, input validation, IDOR
Services with DB access HIGH SQL injection, data exposure
Auth-related files CRITICAL Session, tokens, passwords
External API integrations HIGH SSRF, credential handling
Configuration files MEDIUM Secrets, misconfig
Frontend components MEDIUM XSS, client-side security

Read the full file on GitHub · 458 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 · 458 lines · 0 tokens per session scan A c85370072d32

Subscribe to this mod's changes

security-auditor-agent is an agent published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,630 tokens. 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.