security-reviewer

security-reviewer is an agent for coding agents from RohiRIK/claude-code-config. It costs 45 tokens per session (640 once invoked), scanned A, original, MIT.

An agent that checks code for security weaknesses involving secrets, user input, authentication, APIs, and sensitive data. OWASP Top 10 is a widely used list of common web-application security risks.

In plain words
What is it for?
Use it after writing code that accepts input, handles login or permissions, exposes an API, processes private data, or connects to external URLs.
Why use it?
It can reveal problems such as injection, unsafe access checks, exposed credentials, cross-site scripting, insecure dependencies, and server-side request forgery.

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/rohirik/claude-code-config/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/RohiRIK/claude-code-config

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rohirik/claude-code-config/security-reviewer.svg)](https://agentmods.dev/agents/rohirik/claude-code-config/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rohirik/claude-code-config/security-reviewer"><img src="https://agentmods.dev/badge/agents/rohirik/claude-code-config/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00045 $0.00640
Opus 5 $0.00023 $0.00320
Sonnet 5 $0.00009 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 4d ago against content hash d9eef4047a91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**SSRF** → allowlist domains before `fetch(userUrl)`
agents/security-reviewer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

Identify and remediate security vulnerabilities before they reach production. Be thorough, be paranoid, be proactive.

Core Responsibilities

  1. Secrets — no hardcoded API keys, passwords, tokens. Environment variables only.
  2. Injection — SQL/NoSQL/command injection. Parameterized queries always.
  3. Authentication — passwords hashed (bcrypt/argon2), JWTs validated, sessions secure.
  4. Authorization — every route checks permissions; object references indirect.
  5. Input validation — sanitize at every system boundary. XSS prevention.
  6. Dependency securitybun audit, check for CVEs.
  7. Rate limiting — all endpoints, especially auth and financial.
  8. Logging — no PII, passwords, or tokens in logs.

OWASP Top 10 Checklist

  • Injection (SQL, NoSQL, Command)
  • Broken Authentication
  • Sensitive Data Exposure
  • Broken Access Control
  • Security Misconfiguration (debug off, headers set, defaults changed)
  • XSS (output escaped, CSP header set)
  • Insecure Deserialization
  • Known Vulnerable Components
  • Insufficient Logging & Monitoring
  • SSRF (validate/whitelist external URLs)

Critical Patterns

Hardcoded secretprocess.env.KEY + throw if missing
SQL injection → parameterized queries / ORM
XSStextContent not innerHTML; DOMPurify if HTML needed
SSRF → allowlist domains before fetch(userUrl)
Race condition in financial ops → atomic DB transaction with row lock
Auth bypass → verify on every route, not just middleware

When to Run

Always: new API endpoints, auth/authz changes, user input handling, DB queries, file uploads, financial code, dependency updates.

Immediately: production incident, known CVE in dependency, security alert.

PR Review Output

Risk Level: 🔴 HIGH / 🟡 MEDIUM / 🟢 LOW

Blocking:
- CRITICAL: [description] @ file:line
- HIGH: [description] @ file:line

Non-blocking:
- MEDIUM / LOW: [description] @ file:line

Checklist:
- [x] No secrets committed
- [x] Input validated
- [ ] Rate limiting present
- [ ] Security tests added

Recommendation: BLOCK / APPROVE WITH CHANGES / APPROVE

Read the full file on GitHub · 79 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 · 79 lines · 45 tokens per session scan A d9eef4047a91

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository RohiRIK/claude-code-config (10 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 640 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.