performing-security-testing
关于
This skill automates security testing for applications and APIs, covering OWASP Top 10 vulnerabilities like SQL injection, XSS, and CSRF. It triggers when users request security assessments, penetration tests, or scans using related keywords. Use it to quickly identify authentication, authorization, and other common security flaws.
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-testing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 enables Claude to automatically perform security vulnerability testing on applications and APIs. It leverages the security-test-scanner plugin to identify potential weaknesses and generate comprehensive reports.
How It Works
- Initiate Scan: The plugin is activated when security testing is requested.
- Execute Tests: The plugin automatically runs a suite of security tests covering OWASP Top 10, injection flaws, XSS, CSRF, and authentication/authorization issues.
- Generate Report: The plugin compiles the test results into a detailed report, highlighting vulnerabilities, severity ratings, and remediation steps.
When to Use This Skill
This skill activates when you need to:
- Perform a security vulnerability scan of an application.
- Test for OWASP Top 10 vulnerabilities.
- Identify SQL injection or XSS vulnerabilities.
- Assess authentication and authorization security.
Examples
Example 1: OWASP Top 10 Vulnerability Scan
User request: "Perform a security test focusing on OWASP Top 10 vulnerabilities for the /api/ endpoint."
The skill will:
- Activate the security-test-scanner plugin.
- Execute OWASP Top 10 tests against the specified endpoint.
- Generate a report detailing any identified vulnerabilities and their severity.
Example 2: SQL Injection Testing
User request: "Test the API for SQL injection vulnerabilities."
The skill will:
- Activate the security-test-scanner plugin.
- Run SQL injection tests against the API.
- Report any successful injection attempts.
Best Practices
- Scope Definition: Clearly define the scope of the security test (e.g., specific endpoints, modules).
- Authentication: Provide necessary authentication credentials for testing protected resources.
- Regular Testing: Schedule regular security tests to identify newly introduced vulnerabilities.
Integration
This skill can be integrated with other plugins to automatically trigger security tests as part of a CI/CD pipeline or after code changes. It also integrates with reporting tools for centralized vulnerability management.
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。
