audit · git:20261108.f56f165 · 2026-11-08 · sha256 7bc9d3d1eaba3076

audit git:20261108.f56f165A

Immutable. This exact content never changes and is served at /api/v1/blob/7bc9d3d1eaba3076.

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ccxsbnsjeajxcubp/7bc9d3d1eaba3076c7036bd89e47e797be342334566cafd8f74035acf80127e6.json

Then /plugin install audit@markdownregistry-ccxsbnsjeajxcubp in Claude Code. It installs this exact version, the one graded A here, pinned to the commit it was graded at, and leaves it there.

---
name: audit
description: Security audit of the AI agent setup - Claude Code and agy settings, permissions, hooks, MCP servers, agents, skills and instruction files - for secrets, risky permissions, download-and-run hooks, unpinned servers and prompt injection (no tokens in Claude Code; in agy run `!team audit`)
argument-hint: "[--strict] [--json]"
disable-model-invocation: true
---

In Claude Code a hook answers this command without the model; you only see it when that hook
did not run. Then run `python3 <team skill folder>/scripts/tw.py audit $ARGUMENTS`
from the repository root and show its output. If the user asks for fixes, propose them one by
one and change configuration only after they agree; never print a secret, and tell the user
to rotate any secret the audit found.