Token导航 LogoToken导航

Agent Skill · 研究检索

security(安全)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

security 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 71,838。

总安装 192周安装 8GitHub Stars 17下载 64核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:security(安全)
来源仓库:https://github.com/vinnie357/claude-skills
仓库路径:skills/security
安装命令:
npx skills add https://github.com/vinnie357/claude-skills --skill security
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vinnie357/claude-skills --skill security

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

security 用于辅助安全审计、权限检查、凭据风险和认证流程排查。适合梳理敏感配置、检查依赖风险或生成安全复核清单,不能直接采信工具输出。通过 npx skills add 命令从 GitHub 仓库安装,需指定技能名称和仓库地址。涉及密钥、令牌或生产系统时,应先确认最小权限和脱敏方式。

security 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/security

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/vinnie357/claude-skills --skill security;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

security 怎么安装?

在终端执行 npx skills add https://github.com/vinnie357/claude-skills --skill security。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

security 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

security 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

security 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

security 用的人多吗?

公开数据是累计安装 192 次,近一周安装 8 次,下载 64 次,GitHub 17 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

security 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
security

安全 · 本页

19217接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Security: Secret Detection

This skill activates when performing secret detection, credential scanning, or implementing security checks for leaked sensitive data in code repositories.

When to Use This Skill

Activate when:

  • Scanning repositories for leaked secrets, API keys, or credentials
  • Setting up pre-commit hooks for secret detection
  • Auditing codebases for exposed passwords or tokens
  • Implementing CI/CD security pipelines
  • Checking git history for accidentally committed secrets
  • Validating that.gitignore excludes sensitive files

Pre-Commit Hook (Automatic)

When this skill is loaded, a pre-commit hook automatically scans staged files for secrets before every git commit command. This provides defense-in-depth by catching secrets before they enter git history.

Hook Behavior

git commit -m "message"
         ↓
PreToolUse hook fires
         ↓
Extract staged files
         ↓
Run gitleaks --no-git
         ↓
    ┌─ Clean ─┴─ Secrets ─┐
    ↓                     ↓
  Allow               Block commit
  commit              (exit code 2)

What Gets Scanned

  • Only staged files are scanned (not the entire working tree)
  • Uses .gitleaks-baseline.json if present to ignore known false positives
  • Uses .gitleaks.toml if present for custom detection rules

When Secrets Are Detected

If the hook detects secrets, the commit is blocked with guidance:

[gitleaks] SECRETS DETECTED in staged files!
[gitleaks] Commit blocked. Remove secrets before committing.
[gitleaks]
[gitleaks] Options:
[gitleaks]   1. Remove the secret from the file
[gitleaks]   2. Use environment variables instead
[gitleaks]   3. Add to .gitleaks-baseline.json if false positive

Container Runtime Requirements

The hook requires a container runtime to run gitleaks. It auto-detects:

  1. Apple Container (macOS 26+)
  2. Docker (Docker Desktop or Engine)
  3. Colima via mise

If no runtime is available, the hook logs a warning and allows the commit.

Agent Secret Safety

When agents interact with secrets (1Password, environment variables, keychains):

  • Never print secret values in output, logs, or reports
  • Confirm existence only: test -n "$VAR" && echo "set" || echo "empty"
  • Never use --reveal in agent scripts — use it only in launcher scripts that don't capture output
  • If a secret value is accidentally exposed in conversation context, the user must rotate it immediately

This applies to all agent tiers. A leaked secret in agent output forces credential rotation.

When to Use security-review Instead

Use the security-review skill for:

  • STRIDE threat modeling
  • Security architecture reviews
  • Vulnerability assessments
  • Security documentation and reports
  • Risk prioritization
  • Attack surface analysis
TaskUse securityUse security-review
Scan for secrets in code✓
Detect leaked API keys✓
Pre-commit secret scanning✓
STRIDE threat modeling✓
Security architecture review✓
Vulnerability assessment✓
Security report documentation✓
Risk prioritization✓

Gitleaks

Gitleaks is an open-source tool for detecting secrets and sensitive information in git repositories. It scans commit history and file contents for patterns matching known secret formats.

Common Secrets Detected

  • AWS Access Keys and Secret Keys
  • Google Cloud API Keys
  • GitHub Personal Access Tokens
  • Private Keys (RSA, SSH, PGP)
  • Database Connection Strings
  • JWT Tokens
  • Stripe API Keys
  • Slack Tokens
  • Generic Passwords and API Keys

Basic Usage

# Scan current directory
gitleaks detect --source="." -v

# Scan with JSON report
gitleaks detect --source="." -v --report-path=report.json --report-format=json

# Scan only staged changes (pre-commit)
gitleaks protect --staged

# Scan git history
gitleaks detect --source="." --log-opts="--all"

Configuration

Create a .gitleaks.toml file to customize detection:

[extend]
# Extend default rules
useDefault = true

[[rules]]
id = "custom-api-key"
description = "Custom API Key Pattern"
regex = '''(?i)custom[_-]?api[_-]?key['\"]?\s*[=:]\s*['\"]([a-zA-Z0-9]{32,})'''
keywords = ["custom_api_key", "custom-api-key"]

[allowlist]
paths = [
  '''\.gitleaks\.toml$''',
  '''(.*)?test(.*)''',
  '''\.git'''
]

regexes = [
  '''EXAMPLE_.*''',
  '''REDACTED'''
]

Exit Codes

  • 0: No leaks found
  • 1: Leaks detected
  • Other: Configuration or runtime error

Scripts

This skill includes scripts for running gitleaks with automatic container runtime detection.

gitleaks.nu (Nushell)

Cross-platform Nushell script with automatic runtime detection:

# Run with auto-detected runtime
nu scripts/gitleaks.nu

# Specify runtime
nu scripts/gitleaks.nu --runtime docker
nu scripts/gitleaks.nu --runtime container  # Apple Container (macOS 26+)
nu scripts/gitleaks.nu --runtime colima

# Generate report
nu scripts/gitleaks.nu --report ./report.json

# Use custom config
nu scripts/gitleaks.nu --config ./.gitleaks.toml

# Scan specific path
nu scripts/gitleaks.nu --path ./src

gitleaks.sh (Bash)

Bash script with the same capabilities:

# Run with auto-detected runtime
./scripts/gitleaks.sh

# Specify runtime
./scripts/gitleaks.sh --runtime docker
./scripts/gitleaks.sh -R container

# Generate report
./scripts/gitleaks.sh --report ./report.json

# Use custom config
./scripts/gitleaks.sh --config ./.gitleaks.toml

Container Runtimes

The scripts support three container runtimes with automatic detection:

Detection Priority

  1. Apple Container (macOS 26+) - Native macOS containerization
  2. Docker - Docker Desktop or Docker Engine
  3. Colima - Lightweight container runtime via mise

Apple Container (macOS 26+)

Native container support in macOS 26 and later:

# Check status
container system status

# Start runtime
container system start

# Run gitleaks
container run -v $(pwd):/code zricethezav/gitleaks detect --source="/code" -v

Docker

Docker Desktop or Docker Engine:

# Check status
docker info >/dev/null 2>&1

# Start (macOS)
open -a Docker

# Run gitleaks
docker run -v $(pwd):/code zricethezav/gitleaks detect --source="/code" -v

Colima via mise

Lightweight runtime managed through mise:

# Check status
mise exec colima@latest -- colima status

# Start runtime
mise exec colima@latest -- colima start

# Run gitleaks
mise exec colima@latest -- docker run -v $(pwd):/code zricethezav/gitleaks detect --source="/code" -v

Using mise exec provides automatic installation and version management without requiring global installation.

Pre-Commit Integration

Add gitleaks to pre-commit hooks:

# .pre-commit-config.yaml
repos:
  - repo: https://github.com/gitleaks/gitleaks
    rev: v8.18.0
    hooks:
      - id: gitleaks

Install and run:

pre-commit install
pre-commit run gitleaks --all-files

CI/CD Integration

GitHub Actions

name: Gitleaks

on: [push, pull_request]

jobs:
  gitleaks:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - uses: gitleaks/gitleaks-action@v2
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

GitLab CI

gitleaks:
  stage: security
  image: zricethezav/gitleaks:latest
  script:
    - gitleaks detect --source="." -v
  allow_failure: false

Baseline Management

Create a baseline to ignore known false positives:

# Generate baseline
gitleaks detect --source="." -v --baseline-path=.gitleaks-baseline.json

# Scan using baseline
gitleaks detect --source="." -v --baseline-path=.gitleaks-baseline.json

Add .gitleaks-baseline.json to version control to track acknowledged findings.

Best Practices

Shift-Left Security

  • Enable gitleaks in pre-commit hooks to catch secrets before they enter history
  • Run scans on every PR in CI/CD pipelines
  • Scan regularly even if not making changes

When Secrets Are Found

  1. Revoke immediately - Rotate the exposed credential
  2. Remove from history - Use git filter-branch or BFG Repo Cleaner
  3. Add to.gitignore - Prevent future commits of sensitive files
  4. Update baseline - If false positive, add to baseline

Prevention

  • Use environment variables for secrets
  • Use secret management tools (Vault, AWS Secrets Manager)
  • Add secret patterns to .gitignore
  • Configure IDE plugins to warn about secrets
  • Use .env.example files without real values

Mise Tasks Template

Copy the mise tasks from templates/mise.toml to add gitleaks scanning to any project:

# Available tasks after copying template
mise gitleaks              # Scan with Apple Container (default)
mise gitleaks:docker       # Scan with Docker
mise gitleaks:colima       # Scan with Colima

mise gitleaks:stop         # Stop all runtimes
mise gitleaks:stop:container
mise gitleaks:stop:docker
mise gitleaks:stop:colima

The tasks automatically:

  • Detect and use .gitleaks-baseline.json if present
  • Start the container runtime if not running
  • Scan the repository root

Key Principles

  • Defense in depth: Run checks at multiple stages (local, CI, scheduled)
  • Fail fast: Block PRs with detected secrets
  • Zero tolerance: Treat all secret exposures as security incidents
  • Continuous monitoring: Schedule regular scans of entire history
  • Clear ownership: Define who handles secret remediation

平台分布

Codex

39.31%
按下载量换算25

Claude

28.91%
按下载量换算19

Cursor

17.06%
按下载量换算11

Gemini CLI

10.19%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills