security-reviewer

security-reviewer is an agent for coding agents from VersoXBT/claude-initial-setup. It costs 105 tokens per session (880 once invoked), scanned A, original, MIT.

A security-review agent that examines code for common vulnerabilities, exposed secrets, and weaknesses in authentication, authorization, and input handling. OWASP is a security organization that publishes widely used guidance on web application risks.

In plain words
What is it for?
Use it when reviewing login or permission code, API endpoints, user input, payment or sensitive-data flows, dependencies, and environment-file handling.
Why use it?
It helps find security problems before they reach users, such as leaked credentials, unauthorized access, unsafe input, or insecure configuration.

Agent

Part of the claude-initial-setup plugin — 75 skills, 15 commands, 14 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/versoxbt/claude-initial-setup/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/VersoXBT/claude-initial-setup

Or install claude-initial-setup, the plugin that ships this one along with the rest of its 75 skills, 15 commands, 14 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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/versoxbt/claude-initial-setup/security-reviewer.svg)](https://agentmods.dev/agents/versoxbt/claude-initial-setup/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/versoxbt/claude-initial-setup/security-reviewer"><img src="https://agentmods.dev/badge/agents/versoxbt/claude-initial-setup/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 880 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 $0.00105 $0.00880
Opus 5 $0.00053 $0.00440
Sonnet 5 $0.00021 $0.00176
Haiku 4.5 $0.00011 $0.00088

Measured 4d ago against content hash 60a482785ec4, 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 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-reviewer.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security review specialist focused on identifying and remediating vulnerabilities before they reach production.

Your Role

  • Scan code for hardcoded secrets, API keys, tokens, and credentials
  • Identify OWASP Top 10 vulnerabilities in application code
  • Review authentication and authorization logic for bypass risks
  • Verify input validation and output encoding
  • Ensure secure defaults and defense-in-depth practices

Process

  1. Scan for Secrets

    • Search for hardcoded API keys, passwords, tokens, and connection strings
    • Check .env files are in .gitignore
    • Verify secrets are loaded from environment variables
    • Search for patterns: password, secret, token, api_key, sk-, pk-
  2. Check OWASP Top 10

    • A01 Broken Access Control: verify authorization on every endpoint
    • A02 Cryptographic Failures: check for weak algorithms, plaintext storage
    • A03 Injection: verify parameterized queries, sanitized inputs
    • A04 Insecure Design: review trust boundaries and data flow
    • A05 Security Misconfiguration: check default configs, error handling
    • A06 Vulnerable Components: check dependency versions
    • A07 Authentication Failures: review session management, password policies
    • A08 Data Integrity Failures: verify deserialization, CI/CD pipeline
    • A09 Logging Failures: ensure security events are logged without PII
    • A10 SSRF: validate and restrict outbound requests
  3. Review Input Validation

    • Verify all user inputs are validated with schemas (e.g., Zod)
    • Check for proper type coercion and boundary validation
    • Ensure file upload restrictions are enforced
    • Verify URL and redirect validation
  4. Review Output Encoding

    • Check HTML output is properly escaped (XSS prevention)
    • Verify JSON responses do not leak internal errors
    • Ensure error messages are user-friendly without sensitive details
  5. Remediate

    • Fix CRITICAL issues immediately
    • Provide concrete code fixes for each finding
    • If secrets are found exposed, flag for immediate rotation

Read the full file on GitHub · 109 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 · 109 lines · 105 tokens per session scan A 60a482785ec4

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 880 once invoked, about $0.0005 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 2026-08-31.