security-audit

security-audit is a skill for Claude Code, Codex from ApexIQ/skillsmith. It costs 27 tokens per session (501 once invoked), scanned A, original, MIT.

A code-security review skill based on the OWASP Top 10, a common list of major web-application security risks. It checks areas such as injection, authentication, access control, exposed secrets, and unsafe browser content.

In plain words
What is it for?
Use it to review web code for unsafe inputs, weak login protection, data leaks, incorrect ownership checks, insecure settings, cross-site scripting, and unsafe deserialization.
Why use it?
It provides a checklist for finding security weaknesses that are easy to miss during ordinary feature development.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review web code for unsafe inputs, weak login protection, data leaks, incorrect ownership checks, insecure settings, cross-site scripting, and unsafe deserialization.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/apexiq/skillsmith/security_audit
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.

Any agent
npx skills add ApexIQ/skillsmith --skill security_audit
Clone the repo
git clone --depth 1 https://github.com/ApexIQ/skillsmith

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/apexiq/skillsmith/security_audit.svg)](https://agentmods.dev/skills/apexiq/skillsmith/security_audit)
Your own site
<a href="https://agentmods.dev/skills/apexiq/skillsmith/security_audit"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/security_audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.00501
Opus 5 $0.00014 $0.00251
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 7d ago against content hash effcbdef0778, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

security-audit 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 7d 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.

.agent/skills/security_audit/SKILL.md · 64 lines

What it actually says

🔒 Security Audit

Rule: Assume every input is malicious. Verify everything.

OWASP Top 10 Checklist

1. Injection (SQL, NoSQL, Command)

  • Using parameterized queries? (SQLModel does this automatically)
  • Never concatenating user input into queries?

2. Broken Authentication

  • Passwords hashed with bcrypt/argon2?
  • Session tokens are random and long (>128 bits)?
  • Rate limiting on login endpoints?

3. Sensitive Data Exposure

  • API keys/secrets in environment variables, NOT code?
  • HTTPS enforced?
  • Logging does NOT include passwords or tokens?

4. Broken Access Control (CRITICAL for this app)

  • Ownership check on EVERY resource access?
    if resource.user_id != current_user.id:
        raise HTTPException(404)  # Return 404, not 403
    
  • Admin endpoints require admin role?

5. Security Misconfiguration

  • Debug mode OFF in production?
  • Default credentials changed?
  • CORS restricted to allowed origins?

6. XSS (Cross-Site Scripting)

  • User-generated content sanitized before rendering? (React auto-escapes)
  • dangerouslySetInnerHTML avoided or sanitized?

7. Insecure Deserialization

  • Using Pydantic for all input validation?
  • Not using pickle on untrusted data?

Examples

  • Vulnerable: cursor.execute(f"SELECT * FROM users WHERE id = {user_input}")
  • Secure: cursor.execute("SELECT * FROM users WHERE id = ?", (user_input,))

Guidelines

  • Run bandit (Python) and npm audit (JS) in CI.
  • When in doubt, return 404 instead of 403 (don't leak existence).
  • Log security-relevant events (login attempts, access denials).
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. 7d ago First seen · 64 lines · 27 tokens per session scan A effcbdef0778

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 501 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.