MCP HubMCP Hub
スキル一覧に戻る

scanning-for-vulnerabilities

jeremylongshore
更新日 Yesterday
85 閲覧
712
74
712
GitHubで表示
メタai

について

このスキルは、脆弱性スキャナープラグインを使用したコードベースの自動セキュリティスキャンを可能にします。「脆弱性をスキャンして」や「/scan」などのコマンドでトリガーされ、静的解析、依存関係チェック、CVE検出を実行します。コードの欠陥、脆弱な依存関係、安全でない設定に関する詳細なレポートを取得するためにご利用ください。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus
Git クローン代替
git clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/scanning-for-vulnerabilities

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Overview

This skill empowers Claude to automatically scan your codebase for security vulnerabilities. It leverages the vulnerability-scanner plugin to identify potential risks, including code-level flaws, vulnerable dependencies, and insecure configurations.

How It Works

  1. Initiate Scan: The skill activates the vulnerability-scanner plugin based on user input.
  2. Perform Analysis: The plugin scans the codebase, dependencies, and configurations for vulnerabilities, including CVE detection.
  3. Generate Report: The plugin creates a detailed vulnerability report with findings, severity levels, and remediation guidance.

When to Use This Skill

This skill activates when you need to:

  • Identify security vulnerabilities in your code.
  • Check your project's dependencies for known CVEs.
  • Review your project's configurations for security weaknesses.

Examples

Example 1: Identifying SQL Injection Risks

User request: "Scan my code for SQL injection vulnerabilities."

The skill will:

  1. Activate the vulnerability-scanner plugin.
  2. Analyze the codebase for potential SQL injection flaws.
  3. Generate a report highlighting any identified SQL injection risks and providing remediation steps.

Example 2: Checking for Vulnerable npm Packages

User request: "Check my project's npm dependencies for known vulnerabilities."

The skill will:

  1. Activate the vulnerability-scanner plugin.
  2. Scan the project's package.json file and identify any npm packages with known CVEs.
  3. Generate a report listing the vulnerable packages, their CVE identifiers, and recommended updates.

Best Practices

  • Regular Scanning: Run vulnerability scans regularly, especially before deployments.
  • Prioritize Remediation: Focus on addressing critical and high-severity vulnerabilities first.
  • Validate Fixes: After applying fixes, run another scan to ensure the vulnerabilities are resolved.

Integration

This skill integrates with the core Claude Code environment by providing automated vulnerability scanning capabilities. It can be used in conjunction with other plugins to create a comprehensive security workflow, such as integrating with a ticketing system to automatically create tickets for identified vulnerabilities.

GitHub リポジトリ

jeremylongshore/claude-code-plugins-plus
パス: backups/skills-batch-20251204-000554/plugins/security/vulnerability-scanner/skills/vulnerability-scanner
aiautomationclaude-codedevopsmarketplacemcp

関連スキル

evaluating-llms-harness

テスト

This 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.

スキルを見る

sglang

メタ

SGLang 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.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る

langchain

メタ

LangChain 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.

スキルを見る