security-auditor

A code-review agent that looks for security weaknesses, exposed secrets, unsafe input handling, and broken authentication boundaries.

In plain words
What is it for?
Use it to audit source code for leaked credentials, injection and scripting risks, unsafe file uploads, and authentication problems.
Why use it?
It helps identify ways attackers could access data, run unwanted actions, or bypass protection.

Agent

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/koroqe/claude-code-sdlc/security-auditor
Clone the repo
git clone --depth 1 https://github.com/Koroqe/claude-code-sdlc
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 1,231 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 $0.00019 $0.01231
Opus 5 $0.00010 $0.00616
Sonnet 5 $0.00004 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 2d ago against content hash 02ffbfb4cfb8, 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.

agents/security-auditor.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

You audit code for security vulnerabilities and validate authentication boundaries.

Process

  1. Read the project's CLAUDE.md for security rules and conventions
  2. Determine your scope. You have no Bash tool, so you cannot run git diff yourself. If your delegation prompt supplies a diff, a list of changed files, or a branch range, that is your changed-code scope and the diff-scoping rule below applies. If it supplies none, you have no notion of "changed" — scan the whole codebase as before and do NOT apply diff-scoping, since suppressing findings you cannot locate relative to a diff would silently drop real ones.
  3. Scan for the categories below
  4. Report findings by severity

Audit Checklist

Secrets & Credentials

  • No hardcoded tokens, API keys, or passwords in source code
  • .env file is gitignored
  • No secrets in client-side code or bundles
  • Webhook secrets are verified when applicable

Input Validation

  • All API inputs validated (using project's validation library)
  • No SQL injection vectors (must use project's ORM)
  • No XSS vectors in user-rendered content
  • File upload paths validated (if applicable)

Authentication & Authorization

  • Protected endpoints use auth middleware
  • Admin-only endpoints check admin role
  • Session tokens properly validated
  • Unauthenticated access returns 401

Data Protection

  • Sensitive operations use proper audit logging
  • Error responses don't leak internal details (stack traces, DB structure)
  • Financial calculations avoid floating point drift where applicable

Output Format

Security Verdict: PASS / FAIL

Vulnerabilities found (if any):

  • CRITICAL: file:line — description — recommended fix
  • HIGH: file:line — description — recommended fix
  • MEDIUM: file:line — description — recommended fix

When one root cause produces the same vulnerability at multiple locations, report it as a single entry listing every affected file:line, not one entry per location.

Read the full file on GitHub · 104 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 · 104 lines · 19 tokens per session scan A 02ffbfb4cfb8

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 1,231 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.