security-audit

security-audit is a skill for Claude Code from Enterprise-AI-Circle/agent-skills. It costs 88 tokens per session (2,229 once invoked), scanned A, original, MIT.

A plain-language security review for a codebase, covering common application risks and whether privacy, security, trust, legal, or product claims match the implementation. It can also check areas such as secrets, authentication, cookies, headers, and dependency vulnerabilities.

In plain words
What is it for?
Use it to audit a repository or selected directory before shipping, review authentication and browser protections, find secrets or vulnerable packages, and verify privacy claims.
Why use it?
It catches security problems that are easy to overlook, while adapting the review to the size and purpose of the project. It also warns that fixes affecting access, sessions, or production systems can disrupt working behavior.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the security-audit plugin — 1 skill shipped together

Good fit Use it to audit a repository or selected directory before shipping, review authentication and browser protections, find secrets or vulnerable packages, and verify privacy claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/enterprise-ai-circle/agent-skills/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 Enterprise-AI-Circle/agent-skills --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/Enterprise-AI-Circle/agent-skills

Made for: Claude Code.

Or install security-audit, the plugin that ships this one along with the rest of its 1 skill.

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/enterprise-ai-circle/agent-skills/security-audit/github.svg)](https://agentmods.dev/skills/enterprise-ai-circle/agent-skills/security-audit)
Your own site
<a href="https://agentmods.dev/skills/enterprise-ai-circle/agent-skills/security-audit"><img src="https://agentmods.dev/badge/skills/enterprise-ai-circle/agent-skills/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/enterprise-ai-circle/agent-skills/security-audit"><img src="https://agentmods.dev/badge/skills/enterprise-ai-circle/agent-skills/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,229 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00088 $0.02229
Opus 5 $0.00044 $0.01115
Sonnet 5 $0.00018 $0.00446
Haiku 4.5 $0.00009 $0.00223

Measured 9d ago against content hash 45dcb414c43d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-audit scanned grade A with 1 finding 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 9d 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.

Strips warnings and disclaimerslowAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Do not moralize. The finding is the message.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

agent-skills/security-audit/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security audit

Audit the security basics that would be painful to miss, then check whether the product's privacy and security promises are true in code. Keep the tone plain. The work should feel like a careful engineer reviewed the repo, not like a scanner produced a wall of warnings.

The bar depends on the project. A small side project does not need the same controls as a B2B SaaS that stores customer data. It still should not commit .env, log passwords, or render user input with dangerouslySetInnerHTML.

Functionality matters. Do not suggest a fix that can break a working flow without saying so. Prefer additive fixes when they are enough: add a header, set a cookie flag, redact a log field. Be careful with changes that can lock users out, invalidate sessions, tighten CORS, force 2FA, or touch production infrastructure.

Scope

  • If $ARGUMENTS is a path, scan only that file or directory.
  • Otherwise scan the repo, excluding generated and dependency folders: node_modules, .git, dist, build, out, .next, .nuxt, vendor, target, __pycache__, .venv, lock files, minified assets, and obvious build output from .gitignore.
  • Announce the scope before scanning so the user can redirect you.
  • Detect the stack first. Check manifest files such as package.json, Gemfile, requirements.txt, pyproject.toml, go.mod, Cargo.toml, composer.json, pubspec.yaml, and mix.exs.

Workflow

Progress:

  • Confirm scope and detected stack.
  • Load references/security-checklist.md before the code and config audit.
  • Run the dependency scanner that matches the stack, but only if it is already available.
  • Find privacy and security claims in legal pages, marketing copy, and product UI.
  • Verify each concrete claim against code or configuration evidence.
  • Load references/report-template.md only when writing the report or checking report shape.
  • Validate the report before sending it.
  • Ask the user what to fix. Do not apply changes during the audit unless the user explicitly asks.

Read the full file on GitHub · 145 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 145 lines · 88 tokens per session scan A 45dcb414c43d

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository Enterprise-AI-Circle/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 2,229 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.