audit

A command that reviews the current codebase for common security weaknesses, maps them to OWASP Top 10 and CWE categories, and checks dependencies for known vulnerabilities. OWASP Top 10 is a list of widely seen web security risks; CWE is a catalogue of software weakness types.

In plain words
What is it for?
Use it for a full security review, choosing a development or production-focused report, or auditing a smaller set of changed files with the related audit-diff command.
Why use it?
It helps reveal security problems in application code and third-party packages before they are exploited.

Command

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/sembraniteam/claude-plugins/audit
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00033 $0.01612
Opus 5 $0.00016 $0.00806
Sonnet 5 $0.00007 $0.00322
Haiku 4.5 $0.00003 $0.00161

Measured 2d ago against content hash 98b7c4119738, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

security-auditor/commands/audit.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running a full security audit using the security-auditor plugin. Follow these steps in order.

Step 1 — Determine audit mode

Check if $ARGUMENTS contains a mode hint:

  • dev or development → development mode
  • prod or production → production mode

If no mode is specified, ask the user:

"Is this project currently in development or production?

  • development: verbose output, concrete fix suggestions per finding
  • production: prioritized by exploitability (CVSS + KEV/EPSS where available), executive-ready"

Store the mode and continue once confirmed.

Auditing a pull request or a small changeset? Use /audit-diff instead — it scopes analysis to only the changed files, which is both the most common real-world audit trigger and a way to stay well within context. The rest of this command is for full-codebase scans.

Step 2 — Map project structure

Use Read, Glob, and Grep to build a project map:

  1. Language & framework detection: scan for package.json, requirements.txt, go.mod, pom.xml, Cargo.toml, composer.json, Gemfile, build.gradle, *.csproj — identify the primary stack.
  2. Entry points: locate routes/controllers, input handlers (form submissions, API request bodies, URL params, file uploads), database query files, auth/session files, config files.
  3. Dependency manifests: collect ALL manifest files found — you will query CVEs for each in Step 4.
  4. Secrets surface: scan for .env files, config files with credentials patterns, any hardcoded strings resembling keys/passwords.

Summarize the map to the user before proceeding: "Scanning a [framework] project — found [N] entry points, [N] dependency manifests. Starting code analysis."

Step 3 — Code analysis via subagent

Check this session for findings from an earlier /audit, /audit-file, or /audit-deps run. The security-auditor agent has a fresh context and cannot see them itself, so determine the next unused SA-NNN (or SA-001 if none exist yet) before spawning it.

Read the full file on GitHub · 109 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 First seen · 109 lines · 33 tokens per session scan A 98b7c4119738

Subscribe to this mod's changes

audit is a command published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 33 tokens to every session and 1,612 once invoked, about $0.0002 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.