security-audit

security-audit is a command for Claude Code from rico2035/security-skills. It costs 0 tokens per session (4,302 once invoked), scanned A, original, MIT.

A command that runs security and compliance checks on a codebase. It can inspect the project’s technology and produce a prioritised report with suggested fixes.

In plain words
What is it for?
Use it for full audits or targeted checks covering healthcare data, web security, secrets, tenant separation, audit trails, cryptography, debt-collection calls, and HITRUST.
Why use it?
It gives developers a repeatable way to look for common security problems and compliance gaps before deployment.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the security-audit plugin — 8 skills, 1 command, 1 hook 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/rico2035/security-skills/security-audit
Clone the repo
git clone --depth 1 https://github.com/rico2035/security-skills

Made for: Claude Code.

Or install security-audit, the plugin that ships this one along with the rest of its 8 skills, 1 command, 1 hook.

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/commands/rico2035/security-skills/security-audit.svg)](https://agentmods.dev/commands/rico2035/security-skills/security-audit)
Your own site
<a href="https://agentmods.dev/commands/rico2035/security-skills/security-audit"><img src="https://agentmods.dev/badge/commands/rico2035/security-skills/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 5.1 $0.00000 $0.04302
Opus 5 $0.00000 $0.02151
Sonnet 5 $0.00000 $0.00860
Haiku 4.5 $0.00000 $0.00430

Measured 2d ago against content hash b72ba310c45b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-audit scanned grade A with 2 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| A10 | SSRF | `fetch(.*\${`, `axios.*(.*\${`, `requests.get(.*f"`, user-controlled URL in server-side requests |

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| A03 | Injection | `eval(`, `exec(`, `$queryRawUnsafe`, `.innerHTML =`, `dangerouslySetInnerHTML`, `document.write`, `subprocess.call(.*shell=True` |
plugins/security-audit/commands/security-audit.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/security-audit - Security & Compliance Audit Skill

Job Description

You are a Senior Security & Compliance Engineer. When invoked, you will:

  1. Detect the project's stack (framework, ORM, language)
  2. Determine audit scope (full or targeted)
  3. Run automated scans across the codebase
  4. Cross-reference against compliance frameworks
  5. Generate a prioritized findings report with remediation guidance

Usage

/security-audit                    # Full audit (all enabled modules)
/security-audit hipaa              # PHI/PII leak detection
/security-audit owasp              # OWASP Top 10 scan
/security-audit secrets            # Secrets & config audit
/security-audit tenant             # Tenant isolation check
/security-audit audit-trail        # Audit trail completeness
/security-audit pqc                # PQC cryptography audit (opt-in)
/security-audit fdcpa              # FDCPA/TCPA compliance (opt-in)
/security-audit hitrust            # HITRUST CSF status (opt-in)
/security-audit pre-deploy         # Pre-deployment security gate

Arguments

The module argument arrives as $ARGUMENTS. If $ARGUMENTS is empty, run the full audit: all universal modules, plus opt-in modules only when the project matches their enable conditions.


Step 0: Auto-Detect Project Stack

Before running any module, detect the project's technology stack:

  1. Language: Check for package.json (Node.js), requirements.txt/pyproject.toml (Python), go.mod (Go), Cargo.toml (Rust), pom.xml (Java)
  2. Framework: Check for NestJS (@nestjs/core), Express, Django, FastAPI, Spring Boot, Rails
  3. ORM: Check for Prisma (prisma/schema.prisma), TypeORM, Sequelize, SQLAlchemy, Django ORM
  4. Multi-tenant: Check for tenantId, tenant_id, organization_id patterns in models/schemas
  5. Compliance docs: Check for docs/compliance/, docs/security/, SECURITY.md

Use detected stack to tailor search patterns for each module.


Module 1: PHI/PII Leak Detection (HIPAA)

Read the full file on GitHub · 420 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. 2d ago Changed · +58 lines b72ba310c45b
  2. 6d ago First seen · 362 lines · 0 tokens per session scan A 8109184adac5

Subscribe to this mod's changes

security-audit is a command published in the GitHub repository rico2035/security-skills (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,302 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.