Security Audit Review — Security skill for Claude Code
Performs deep security audits on any codebase — finds vulnerabilities, exploits, and attack vectors.
How to install Security Audit Review
Installs to ~/.claude/skills/josipmusa-jds-security-audit-review/SKILL.md
mkdir -p ~/.claude/skills/josipmusa-jds-security-audit-review && curl -fsSL https://raw.githubusercontent.com/josipmusa/jds/HEAD/commands/security-audit-review.md -o ~/.claude/skills/josipmusa-jds-security-audit-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Security Audit Review does
description: Performs deep security audits on any codebase — finds vulnerabilities, exploits, and attack vectors. Supports branch/PR comparison or full project scans. Read-only analysis; produces a report only, never modifies code. argument-hint: Branch, PR number, file path, or empty for full project audit (e.g. "PR #142", "feature/auth vs main", "src/payments") allowed-tools: Read, Grep, Glob, LS, Bash(git diff:*), Bash(git log:*), Bash(git show:*), Bash(git fetch:*)
You are a READ-ON
Alternatives in Security
- Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
- Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
- Tech Debt Skill — Claude Code skill that produces a thorough, file-cited tech debt audit of an entire codebase 590 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Auxi Figma Audit
3-pass Figma design audit for the Auxi RN app. Given a Figma URL + target screen, runs Pass 1 (Figma deep extr
Slowmist Security Cc
SlowMist Security Review — comprehensive security framework for Claude Code agents. 6 review types, 18 PI vect
Swift Arch Check
Read-only architecture audit. Scans the project and produces a structured report. Makes NO changes to any file
Review AI Agent Surface
Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and uns
Skill Threat Modeling
Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr
Branch Audit
Read-only audit of local branches, worktrees, and PR state. Classifies each as fully-merged / unique-work / st
Related Agents
Paranoid Sentinel
A hyper-vigilant security code reviewer with paranoid delivery - performs thorough security analysis first, th
Code Reviewer Security
Use this agent when you need deep security analysis of code changes. Focuses exclusively on vulnerabilities, e
Production Security Auditor
Audits codebase for security vulnerabilities — OWASP Top 10 detection, secrets exposure, injection vectors, au