performing-security-code-review
关于
This skill enables Claude to perform automated security code reviews using the security-agent plugin. It detects vulnerabilities like SQL injection and XSS, providing structured findings with severity ratings and remediation guidance. Use it when requesting a security audit or reviewing code for security concerns.
快速安装
Claude Code
推荐/plugin add https://github.com/jeremylongshore/claude-code-plugins-plusgit clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/performing-security-code-review在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Overview
This skill empowers Claude to act as a security expert, identifying and explaining potential vulnerabilities within code. It leverages the security-agent plugin to provide detailed security analysis, helping developers improve the security posture of their applications.
How It Works
- Receiving Request: Claude identifies a user's request for a security review or audit of code.
- Activating Security Agent: Claude invokes the security-agent plugin to analyze the provided code.
- Generating Security Report: The security-agent produces a structured report detailing identified vulnerabilities, their severity, affected code locations, and recommended remediation steps.
When to Use This Skill
This skill activates when you need to:
- Review code for security vulnerabilities.
- Perform a security audit of a codebase.
- Identify potential security risks in a software application.
Examples
Example 1: Identifying SQL Injection Vulnerability
User request: "Please review this database query code for SQL injection vulnerabilities."
The skill will:
- Activate the security-agent plugin to analyze the database query code.
- Generate a report identifying potential SQL injection vulnerabilities, including the vulnerable code snippet, its severity, and suggested remediation, such as using parameterized queries.
Example 2: Checking for Insecure Dependencies
User request: "Can you check this project's dependencies for known security vulnerabilities?"
The skill will:
- Utilize the security-agent plugin to scan the project's dependencies against known vulnerability databases.
- Produce a report listing any vulnerable dependencies, their Common Vulnerabilities and Exposures (CVE) identifiers, and recommendations for updating to secure versions.
Best Practices
- Specificity: Provide the exact code or project you want reviewed.
- Context: Clearly state the security concerns you have regarding the code.
- Iteration: Use the findings to address vulnerabilities and request further reviews.
Integration
This skill integrates with Claude's code understanding capabilities and leverages the security-agent plugin to provide specialized security analysis. It can be used in conjunction with other code analysis tools to provide a comprehensive assessment of code quality and security.
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
creating-opencode-plugins
元该Skill为开发者创建OpenCode插件提供指导,涵盖命令、文件、LSP等25+种事件类型。它详细说明了插件结构、事件API规范及JavaScript/TypeScript实现模式,帮助开发者构建事件驱动的模块。适用于需要拦截操作、扩展功能或自定义AI助手行为的插件开发场景。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
evaluating-llms-harness
测试该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。
