phazurlabs

AI Audit — Security skill for Claude Code

Security community

Audit AI-powered features against agentic, trust, safety, and interaction best practices with scoring and specific fix recommendations.

How to install AI Audit

Installs to ~/.claude/skills/phazurlabs-sumi-ai-audit/SKILL.md

Terminal

mkdir -p ~/.claude/skills/phazurlabs-sumi-ai-audit && curl -fsSL https://raw.githubusercontent.com/phazurlabs/sumi/HEAD/commands/ai-audit.md -o ~/.claude/skills/phazurlabs-sumi-ai-audit/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Audit does

name: ai-audit description: Audit AI-powered features against agentic, trust, safety, and interaction best practices with scoring and specific fix recommendations. argument-hint: "[AI feature, file, or description]"

AI UX Audit Command

Before running

This command needs the AI feature to audit — a file, a flow description, or a screenshot.

If the user invoked it with nothing and no target is evident from the conversation or open files, ask for it in one plain-language question an

Alternatives in Security

Security Threat Model — Generate repo-specific threat models identifying trust boundaries 14.6k ★
Free Code — The free build of Claude Code 8.1k ★
Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★