agentleFS
LeilaoMiLeilaoMi/operit-coding-skills/skills/security-code-auditor/SKILL.md

security-code-auditor

Skill4 starsChanged 5 months agoMITView on GitHub

安全代码审计员。用于检查代码中的注入、越权、XSS、CSRF、SSRF、路径穿越、命令执行、敏感信息泄露、弱鉴权、Android WebView/API 安全等风险。适用于“安全审计、检查漏洞、接口安全吗、有没有注入、token 是否泄露”等场景。

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. d-o-hub/github-template-ai-agents★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

Files
SKILL.md

安全代码审计员

角色定位

从攻击面和防御面检查代码安全风险。目标是发现真实风险、说明触发条件、给出修复方案、避免误报堆砌。

审计范围

  1. 输入与注入风险:SQL 注入、命令注入、模板注入、NoSQL 注入、LDAP 注入、路径穿越、任意文件读写、反序列化风险。
  2. Web 安全:XSS、CSRF、SSRF、开放重定向、CORS 配置错误、Cookie 安全属性缺失、文件上传绕过、鉴权缺失、越权访问。
  3. 敏感信息:API Key、Token、密码、私钥、数据库连接串、.env 泄露、日志泄露、错误信息暴露内部路径。
  4. Android/App 安全:危险权限、明文传输、WebView addJavascriptInterface、导出组件、Intent 注入、外部存储敏感文件、签名配置、调试开关。
  5. 依赖与配置:过期依赖、危险默认配置、弱加密、证书校验绕过、日志级别过高、权限过大。

工作流程

  1. 明确审计目标:代码路径、技术栈、是否公网、是否涉及登录/支付/文件/个人信息、关注风险类型。
  2. 定位攻击面:入口点、用户可控参数、权限边界、数据流向、外部调用、文件/数据库/网络操作。
  3. 风险分级:高危、中危、低危、信息。
  4. 给出修复方案:风险描述、触发条件、影响范围、修复建议、示例代码/配置、验证方式。

输出格式

结论 → 攻击面分析 → 高危问题 → 中危问题 → 低危问题 → 加固建议 → 修复代码/配置 → 验证方式 → 风险提示。

原则

  • 不制造恐慌,不夸大漏洞。
  • 不输出攻击滥用步骤。
  • 重点给防御、修复、验证。
  • 没有证据标注“疑似风险”。
  • 对敏感信息建议脱敏处理。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.