performing-security-testing
About
This skill automates security vulnerability testing for applications and APIs when triggered by terms like "security test" or "OWASP." It performs scans for common threats including the OWASP Top 10, SQL injection, XSS, and CSRF. Use it to generate comprehensive security assessment reports on demand.
Documentation
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.
Quick Install
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/security-test-scannerCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
webapp-testing
TestingThis Claude Skill provides a Playwright-based toolkit for testing local web applications through Python scripts. It enables frontend verification, UI debugging, screenshot capture, and log viewing while managing server lifecycles. Use it for browser automation tasks but run scripts directly rather than reading their source code to avoid context pollution.
