audit-security

audit-security is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 26 tokens per session (1,781 once invoked), scanned A, original, MIT.

A command that checks a codebase for security problems, including exposed secrets, common web vulnerabilities, unsafe configuration, and vulnerable dependencies.

In plain words
What is it for?
Use it to audit a whole project or selected files, including environment settings, Docker and CI files, and package dependencies.
Why use it?
It brings together code, configuration, and dependency checks so issues such as injection, weak authentication, leaked keys, or outdated packages are easier to find.

Command for Claude Code

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/kumaran-is/claude-code-onboarding/audit-security
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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 audit-security

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/audit-security.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/audit-security)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/audit-security"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/audit-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00026 $0.01781
Opus 5 $0.00013 $0.00890
Sonnet 5 $0.00005 $0.00356
Haiku 4.5 $0.00003 $0.00178

Measured today against content hash c50fef72bf8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-security 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 today.

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.

.claude/commands/audit-security.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit

Run a comprehensive security audit on the codebase.

Process

  1. Determine scope — audit $ARGUMENTS if provided, otherwise audit the full project

  2. Delegate to security-reviewer agent with the following checks:

    • Hardcoded secrets, API keys, tokens, passwords
    • OWASP Top 10 vulnerabilities (injection, XSS, SSRF, broken auth, etc.)
    • Unsafe deserialization or eval usage
    • Missing input validation at system boundaries
    • Insecure cryptographic practices
    • Exposed debug endpoints or verbose error messages in production
  3. Check configuration files:

    • .env files not in .gitignore
    • Secrets in docker-compose.yml or CI config
    • Overly permissive CORS or security headers
  4. Check dependencies (if applicable):

    • Run npm audit for Node.js projects
    • Run pip audit for Python projects
    • Flag known CVEs in pom.xml dependencies
  5. Dependency vulnerability scan (deep scan):

    Run the dependency scanner for a comprehensive CVE analysis with priority scoring:

    /security-dependencies $ARGUMENTS
    

    Include the top 5 highest-priority CVEs (by priority score) in the final report. Flag any CVSS 9+ findings as blocking -- do not approve the release until resolved.

  6. Agentic CI/CD audit (if .github/workflows/ directory exists):

    Load skill: claude-actions-auditor

    Glob .github/workflows/*.yml and .github/workflows/*.yaml. If any workflow file contains anthropics/claude-code-action, run the full 5-step audit from the claude-actions-auditor skill.

    Add findings to the final report under a new section:

    ### Agentic CI/CD
    - [workflow-file:line] [vector name] [description]
    

    If no workflows or no Claude Code Action steps found: note "No Claude Code Action workflows detected — agentic CI/CD audit skipped."

  7. Compute 007 Security Score (run after all findings are collected from steps 2–6):

    Calculate a 0–100 weighted score across 8 domains. For each domain, start at 100 and apply deductions:

    • CRITICAL finding in domain: −15 pts
    • HIGH finding in domain: −8 pts
    • MEDIUM finding in domain: −3 pts
    • LOW finding in domain: −1 pt
    • Floor at 0 per domain

Read the full file on GitHub · 184 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. today First seen · 184 lines · 26 tokens per session scan A c50fef72bf8e

Subscribe to this mod's changes

audit-security is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,781 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 2026-09-03.