Skip to content
Development
Command

/audit

Perform a security audit of the codebase covering common vulnerability categories.

From plugin
rohitg00-claude-code-toolkit
2.5k199 skills138 agents199 commands
Install
$ npx -y skills add rohitg00/awesome-claude-code-toolkit --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/audit

Context preview

What this command does when you run it.

Perform a security audit of the codebase covering common vulnerability categories.

Command definition

audit.md

Perform a security audit of the codebase covering common vulnerability categories.

Steps

1. Dependency Vulnerabilities

  • Run the package manager's audit: `npm audit`, `pip audit`, `cargo audit`, `govulncheck ./...`.
  • List critical and high severity vulnerabilities.
  • For each, determine if the vulnerable code path is actually reachable in this project.
  • Recommend specific version upgrades or patches.

2. Secrets Scan

  • Search for hardcoded secrets, API keys, tokens, and passwords:
  • Patterns: `password\s*=`, `api[_-]?key`, `secret`, `token`, `Bearer `, base64-encoded strings.
  • Files: `.env` files committed to git, config files, source code.
  • Check `.gitignore` for proper exclusion of sensitive files.
  • Verify environment variables are used for all secrets.

3. OWASP Top 10 Check

  • **Injection**: SQL injection, command injection, XSS. Search for string concatenation in queries, `eval()`, `innerHTML`.
  • **Broken Auth**: Weak password policies, missing rate limiting, session fixation.
  • **Sensitive Data Exposure**: Unencrypted data at rest/transit, verbose error messages, logs containing PII.
  • **Broken Access Control**: Missing authorization checks, IDOR vulnerabilities, privilege escalation paths.
  • **Security Misconfiguration**: Default credentials, unnecessary features enabled, CORS wildcards.

4. Input Validation

  • Verify all user inputs are validated before processing.
  • Check for proper type coercion and boundary checking.
  • Ensure file uploads have type, size, and name validation.
  • Verify URL and redirect validation prevents open redirects.

5. Authentication and Authorization Review

  • Check password hashing (bcrypt/argon2, not MD5/SHA1).
  • Verify JWT token expiration and rotation.
  • Check for proper CSRF protection.
  • Verify role-based access control at the API layer, not just the UI.

6. Report

Produce a findings report organized by severity (Critical, High, Medium, Low, Info) with:

  • Finding description.
  • Affected file and line.
  • Recommended fix.
  • Reference (CWE number or OWASP category).

Rules

  • Prioritize findings by exploitability and impact, not just theoretical risk.
  • Include proof-of-concept for critical findings when safe to do so.
  • Do not just list tools to run. Actually analyze the output and provide actionable recommendations.
  • Check both the application code and infrastructure configuration (Dockerfiles, CI configs, cloud configs).
Read more
Ships withrohitg00-claude-code-toolkit

The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.

Get the whole plugin