security-check

A command that audits a codebase against OWASP security guidance, a widely used set of practices for finding web-application risks.

In plain words
What is it for?
Use it to review API and form validation, authentication, file uploads, password handling, tokens, database queries, and related project settings.
Why use it?
It helps surface common problems such as exposed secrets, weak input checks, missing access controls, and injection vulnerabilities.

Command

Part of the claude-initial-setup plugin — 24 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 commands/versoxbt/claude-initial-setup/security-check
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 24 skills, 15 commands, 14 agents, 2 hooks.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 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 $0.00010 $0.00569
Opus 5 $0.00005 $0.00284
Sonnet 5 $0.00002 $0.00114
Haiku 4.5 $0.00001 $0.00057

Measured 3d ago against content hash 498e5ca0dab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-check 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 3d 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.

commands/security-check.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Check

Perform a comprehensive security audit based on OWASP guidelines to identify vulnerabilities.

Steps

  1. Scan for hardcoded secrets:

    • Search for API keys, passwords, tokens, and connection strings in source files.
    • Check for patterns like sk-, api_key =, password =, secret =, token =.
    • Review .env.example to ensure no real values are committed.
    • Verify .gitignore includes .env, credentials files, and key files.
  2. Check input validation:

    • Review all API endpoints and form handlers.
    • Verify all user inputs are validated with a schema (zod, joi, etc.).
    • Check that validation happens on the server side, not just client side.
    • Ensure file uploads are restricted by type and size.
  3. Review authentication and authorization:

    • Verify authentication is required on all protected routes.
    • Check that authorization checks enforce proper access levels.
    • Ensure passwords are hashed with bcrypt, argon2, or scrypt (never MD5 or SHA1).
    • Verify session tokens and JWTs have proper expiration.
  4. Check for injection vulnerabilities:

    • SQL injection: Verify all queries use parameterized statements or an ORM.
    • NoSQL injection: Check that user input is not passed directly to query operators.
    • Command injection: Ensure no user input reaches shell commands or exec calls.
  5. Check for XSS vulnerabilities:

    • Verify HTML output is escaped or sanitized.
    • Check that dangerouslySetInnerHTML or equivalent is not used with user input.
    • Review Content-Security-Policy headers.
  6. Check for CSRF protection:

    • Verify CSRF tokens are used on state-changing requests.
    • Check SameSite cookie attributes.
  7. Review error handling:

    • Ensure error messages do not expose stack traces, file paths, or internal details to users.
    • Verify that generic error messages are returned in production.
  8. Check dependencies:

    • Run npm audit, pip audit, or equivalent for the project's package manager.
    • Review any HIGH or CRITICAL vulnerabilities.
    • Check for outdated dependencies with known CVEs.

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 10 tokens per session scan A 498e5ca0dab4

Subscribe to this mod's changes

security-check is a command published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 569 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 2026-08-31.