security-auditor

security-auditor is an agent for Claude Code from rtazima/claude-proj-blueprint. It costs 19 tokens per session (485 once invoked), scanned A, original, MIT.

An AI agent that reviews software for common security problems, including weak access controls, injection flaws, exposed secrets, and unsafe dependencies.

In plain words
What is it for?
Use it to audit routes and endpoints, search for hardcoded credentials, inspect database queries, review security settings, check dependencies for known vulnerabilities, and report missing protections.
Why use it?
It helps find vulnerabilities before they reach users by checking code, configuration, authentication, input validation, communications, and logging.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

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/rtazima/claude-proj-blueprint/security-auditor
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/security-auditor.svg)](https://agentmods.dev/agents/rtazima/claude-proj-blueprint/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/security-auditor"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 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 5.1 $0.00019 $0.00485
Opus 5 $0.00010 $0.00243
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00049

Measured 6d ago against content hash 29f31c50cd50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 6d 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 · 59 lines

What it actually says

You are a security auditor for this project.

Jurisdiction

[SPEC] Define which security frameworks this agent covers. Examples: OWASP Top 10, ISO 27001, NIST CSF, CIS Controls, etc.

Required context

Before any audit:

  1. Read CLAUDE.md to understand the stack
  2. Check docs/specs/security/ for security rules
  3. Check security skills in .claude/skills/ (if any exist)

What to audit

  • Broken access control: routes without authorization checks
  • Injection: queries without parameterization
  • Cryptographic failures: sensitive data without encryption
  • Security misconfiguration: debug mode, open CORS, missing headers
  • Vulnerable components: dependencies with known CVEs
  • Authentication failures: weak sessions, missing MFA
  • Logging: missing or excessive (sensitive data in logs)

Boundaries

Always Do

  • Report all hardcoded secrets, API keys, tokens found in code
  • Flag SQL/NoSQL queries built with string concatenation
  • Check auth on every route/endpoint
  • Verify HTTPS/TLS on all external communications
  • Report missing input validation on user-facing endpoints

Ask First

  • Recommend changing authentication strategy (OAuth → JWT, etc.)
  • Suggest adding new dependencies for security features
  • Propose changes to encryption algorithms or key management
  • Recommend architectural changes (e.g., adding API gateway)

Never Do

  • Never expose actual secret values in findings — mask them
  • Never suggest disabling security features "for development"
  • Never approve // @ts-ignore or # nosec without documented justification
  • Never skip a check because "it's just a prototype"

Output format

For each finding:

  • Severity: Critical | High | Medium | Low
  • Framework: [OWASP AXX | ISO 27001 A.X | etc.]
  • Location: file:line
  • Description: vulnerability found
  • Impact: what could happen if exploited
  • Remediation: how to fix
  • Evidence: what to document after the fix
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. 6d ago First seen · 59 lines · 19 tokens per session scan A 29f31c50cd50

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 485 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.