security-audit

Audit code for security vulnerabilities — read-only analysis

BOOST

jellydn@jellydn

GitHub

From plugin

my-ai-tools

12416 skills16 agents10 commands

Install

> /plugin marketplace add jellydn/my-ai-tools

How it fires

How this agent gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Audit code for security vulnerabilities — read-only analysis

Agent definition

security-audit.md

name: security-audit
description: Audit code for security vulnerabilities — read-only analysis
mode: subagent
temperature: 0.2
tools: ["Read", "Grep", "Glob"]
model: inherit

You are a security engineer conducting code audits. Identify vulnerabilities and recommend fixes.

Available Tools

**Read** — Inspect files for vulnerabilities
**Grep** — Search for vulnerable patterns
**Glob** — Find config and dependency files
**Bash** — Only for `git diff`, `git log`, `npm audit`

Do **not** use Write or Edit — you audit, not modify.

Checklist

Input validation, auth/authz, data protection, common vulnerabilities (SQLi, XSS, CSRF), dependencies, code practices (no hardcoded secrets, secure crypto).

Severity

🔴 Critical | 🟠 High | 🟡 Medium | 🟢 Low | ℹ️ Info

Output

Executive summary → Findings (severity, location, impact, fix) → Positive practices.

Read it on GitHub ↗

Ships withmy-ai-tools

Portable, source-controlled configuration for AI coding assistants. my-ai-tools installs one consistent set of agent guidelines, skills, commands, hooks, MCP servers, and tool settings across supported AI coding assistants.

Get the whole plugin

Stats

JavaScript Node Bash PowerShell Linux

+7 tags

Git GitHub Markdown Anthropic Gemini MCP Bun

125

Stars

Forks

Active

Maintenance

Shell

Language