安全评审官

Security vulnerability detection and remediation specialist. Flags secrets, injection, SSRF, unsafe crypto, and OWASP Top 10 vulnerabilities before they reach production. Use proactively on code handling user input, auth, API endpoints, or sensitive data.

Author
Jason
Type
agent
Category
qa
Version
1.0.0
Tags
安全, 漏洞检测, OWASP, 代码审查, secrets, 渗透, 研发安全
Price
Free

README

# Security Reviewer (安全评审官) ## Overview **Security Reviewer (安全评审官)** is a security vulnerability detection and remediation specialist. It proactively reviews code that handles user input, authentication, API endpoints, or sensitive data — flagging secrets, injection, SSRF, unsafe crypto, and OWASP Top 10 vulnerabilities before they reach production. ## Key Capabilities - ✅ **OWASP Top 10 checks** — injection, broken auth, sensitive data, XXE, access control, misconfig, XSS, deserialization, known vulns, logging - ✅ **Secrets detection** — finds hardcoded API keys, passwords, tokens via pattern scanning - ✅ **Code pattern review** — instant severity-tagged findings with concrete secure fixes - ✅ **Emergency response** — immediate alerting on CRITICAL vulnerabilities - ✅ **General QA Review** — structured reports with file:line evidence ## Usage 1. Load the `security-reviewer` agent into your workspace. 2. @mention `@security-reviewer` (or route via workflow) after code involving user input, auth, or sensitive data. 3. Agent returns a structured finding list: severity / location / fix, and verifies remediation. ## Licensing Source Based on the **security-reviewer** role definition from [everything-claude-code](https://github.com/affaan-m/everything-claude-code) (MIT). --- **Attribution:** Based on [security-reviewer agent](https://github.com/affaan-m/everything-claude-code/blob/main/agents/security-reviewer.md) from [everything-claude-code](https://github.com/affaan-m/everything-claude-code) - Original author: Affaan Mustafa - License: MIT