MCP HubMCP Hub
スキル一覧に戻る

scanning-for-secrets

jeremylongshore
更新日 Today
88 閲覧
712
74
712
GitHubで表示
メタwordapi

について

このスキルは、パターンマッチングとエントロピー分析を用いて、APIキーやパスワードなどの漏洩したシークレットをコードベース内でスキャンします。コードがコミットまたはデプロイされる前に、開発者がセキュリティ脆弱性を事前に特定し対処することを支援します。「シークレットをスキャンして」や「漏洩した認証情報をチェックして」などのトリガーフレーズで使用できます。

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-secrets

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 enables Claude to scan your codebase for exposed secrets, API keys, passwords, and other sensitive credentials. It helps you identify and remediate potential security vulnerabilities before they are committed or deployed.

How It Works

  1. Initiate Scan: Claude activates the secret-scanner plugin.
  2. Codebase Analysis: The plugin scans the codebase using pattern matching and entropy analysis.
  3. Report Generation: A detailed report is generated, highlighting identified secrets, their locations, and suggested remediation steps.

When to Use This Skill

This skill activates when you need to:

  • Scan your codebase for exposed API keys (e.g., AWS, Google, Azure).
  • Check for hardcoded passwords in configuration files.
  • Identify potential private keys (SSH, PGP) accidentally committed to the repository.
  • Proactively find secrets before committing changes.

Examples

Example 1: Identifying Exposed AWS Keys

User request: "Scan for AWS keys in the codebase"

The skill will:

  1. Activate the secret-scanner plugin.
  2. Scan the codebase for patterns matching AWS Access Keys (AKIA[0-9A-Z]{16}).
  3. Generate a report listing any found keys, their file locations, and remediation steps (e.g., revoking the key).

Example 2: Checking for Hardcoded Passwords

User request: "Check for exposed credentials in config files"

The skill will:

  1. Activate the secret-scanner plugin.
  2. Scan configuration files (e.g., database.yml, .env) for password patterns.
  3. Generate a report detailing any found passwords and suggesting the use of environment variables.

Best Practices

  • Regular Scanning: Schedule regular scans to catch newly introduced secrets.
  • Pre-Commit Hooks: Integrate the secret-scanner into your pre-commit hooks to prevent committing secrets.
  • Review Entropy Analysis: Carefully review results from entropy analysis, as they may indicate potential secrets not caught by pattern matching.

Integration

This skill can be integrated with other security tools, such as vulnerability scanners, to provide a comprehensive security assessment of your codebase. It can also be combined with notification plugins to alert you when new secrets are detected.

GitHub リポジトリ

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

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

スキルを見る

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

polymarket

メタ

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

スキルを見る