Token导航 LogoToken导航

Agent Skill · 研究检索

security-audit(安全审计)

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-audit 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,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 63,559。

总安装 315周安装 13GitHub Stars 8下载 103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-audit(安全审计)
来源仓库:https://github.com/ar4mirez/samuel
仓库路径:skills/security-audit
安装命令:
npx skills add https://github.com/ar4mirez/samuel --skill security-audit
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/ar4mirez/samuel --skill security-audit

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-audit 用于辅助安全审计、权限检查和常见漏洞排查,适合梳理敏感配置和分析鉴权逻辑。适用于 OWASP Top 10 漏洞检测、依赖风险分析和凭据安全管理,支持生产环境部署前的安全检查。通过 npx skills add 命令从指定 GitHub 仓库安装,需结合项目依赖和认证流程使用。

不能将工具输出直接作为最终结论,涉及密钥或用户数据时应先确认最小权限和操作边界。当前无详细 SKILL.md 内容,需参考仓库中的 Security Audit Skill 了解审计范围和优先级划分。

来源仓库内路径:skills/security-audit

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/ar4mirez/samuel --skill security-audit;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-audit 怎么安装?

在终端执行 npx skills add https://github.com/ar4mirez/samuel --skill security-audit。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

security-audit 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-audit 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-audit 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-audit 用的人多吗?

公开数据是累计安装 315 次,近一周安装 13 次,下载 103 次,GitHub 8 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-audit 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

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-audit

安全审计 · 本页

3158接触敏感数据未明确通过

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 Audit Skill

Proactive security assessment covering OWASP Top 10, dependency vulnerabilities, secrets detection, and security best practices.


When to Use

TriggerPriorityDescription
Pre-ProductionCriticalBefore any production deployment
Monthly ReviewHighRegular security hygiene
Auth ChangesCriticalAfter adding/modifying authentication
External IntegrationHighWhen adding third-party services
Dependency UpdatesMediumAfter major dependency changes
Security IncidentCriticalPost-incident review

Audit Scope

Full Audit

Complete security review across all categories. Time: 2-4 hours.

Focused Audit

Target specific area (e.g., authentication only). Time: 30-60 minutes.

Quick Scan

Automated checks only (dependencies, secrets). Time: 5-10 minutes.


Prerequisites

Before starting audit:

  • Access to codebase and dependencies
  • Access to environment configuration (sanitized)
  • List of external services/APIs used
  • Authentication flow documentation (if exists)
  • Previous audit reports (if available)

Audit Process

Phase 1: OWASP Top 10 Review
    ↓
Phase 2: Dependency Vulnerability Scan
    ↓
Phase 3: Secrets Detection
    ↓
Phase 4: Input Validation Audit
    ↓
Phase 5: Authentication & Authorization
    ↓
Phase 6: API Security
    ↓
Phase 7: Report & Remediation

Phase 1: OWASP Top 10 Review

Quick Reference

IDCategoryKey Check
A01Broken Access ControlAuthorization on all endpoints
A02Cryptographic FailuresTLS, password hashing, encryption
A03InjectionParameterized queries, input escaping
A04Insecure DesignDefense in depth, trust boundaries
A05Security MisconfigurationHeaders, defaults, error messages
A06Vulnerable ComponentsDependency scanning
A07Authentication FailuresPassword policy, session security
A08Data IntegrityChecksums, secure CI/CD
A09Logging FailuresSecurity event logging
A10SSRFURL validation, network restrictions

For detailed patterns and examples: See references/process.md

Critical Checks

A01 - Broken Access Control:

- [ ] All endpoints have authorization checks
- [ ] RBAC implemented
- [ ] No direct object reference vulnerabilities
- [ ] Privilege escalation prevented

A02 - Cryptographic Failures:

- [ ] Passwords hashed with bcrypt/argon2 (cost 10+)
- [ ] TLS 1.2+ enforced
- [ ] Sensitive data encrypted at rest
- [ ] Cryptographically random tokens

A03 - Injection:

- [ ] SQL queries use parameterized statements
- [ ] Template engines auto-escape output
- [ ] No shell command execution with user input
- [ ] NoSQL queries sanitized

A05 - Security Misconfiguration:

Required Headers:
- X-Content-Type-Options: nosniff
- X-Frame-Options: DENY
- Content-Security-Policy: default-src 'self'
- Strict-Transport-Security: max-age=31536000

Phase 2: Dependency Vulnerability Scan

Run Audit Commands

# Node.js
npm audit
npm audit --audit-level=moderate

# Python
pip-audit
# Or: safety check --json > audit-report.json

# Go
govulncheck ./...

# Rust
cargo audit

# Ruby
bundle audit check

Severity Response

SeverityActionTimeline
CriticalImmediate fix or removeHours
HighFix in current sprintDays
ModerateSchedule fixWeeks
LowTrack for updateNext release

Phase 3: Secrets Detection

Automated Scanning

# Using gitleaks (recommended)
gitleaks detect --source . --verbose

# Using git-secrets
git secrets --scan
git secrets --scan-history

# Using truffleHog
trufflehog filesystem .

Common Secret Patterns

PatternExampleRisk
API Keyssk_live_, AKIAHigh
Passwordspassword=, passwdCritical
Tokenstoken=, bearerHigh
Private Keys-----BEGIN RSACritical
AWS Credentialsaws_access_key_idCritical

Environment Variables

Checklist:
- [ ] All secrets in environment variables (not code)
- [ ] .env files in .gitignore
- [ ] No .env files in git history
- [ ] Secure defaults for all variables

Phase 4: Input Validation Audit

Input Sources by Risk

SourceExamplesRisk
File uploadsImages, documentsCritical
Request bodyJSON, form dataHigh
URL parameters/users/:idHigh
Query strings?search=termHigh
HeadersCustom headersMedium
CookiesSession cookiesMedium

Validation Checklist

For each input:

  • Schema validation (Zod, Pydantic, etc.)
  • Type checking enforced
  • Length/size limits
  • Format validation (email, URL)
  • Allowlist when possible
  • Sanitized for output context

File Upload Requirements

- [ ] Magic bytes validation (not just extension)
- [ ] Size limits enforced
- [ ] Virus/malware scanning
- [ ] Storage outside web root
- [ ] Randomized filenames
- [ ] No executable permissions

Phase 5: Authentication & Authorization

Password Security

- [ ] Min length: 12+ characters
- [ ] Bcrypt (cost 10+) or argon2
- [ ] No passwords in logs/errors
- [ ] Rate limiting on login
- [ ] Account lockout policy

Session Security

- [ ] HttpOnly cookie flag
- [ ] Secure cookie flag (HTTPS)
- [ ] SameSite attribute
- [ ] Session timeout
- [ ] Invalidation on logout
- [ ] Regenerate on privilege change

Authorization

- [ ] Check on every endpoint
- [ ] RBAC implemented
- [ ] Least privilege
- [ ] Deny by default
- [ ] Server-side validation

Token Security (JWT/OAuth)

- [ ] Strong algorithm (RS256, ES256)
- [ ] Token expiration
- [ ] Refresh mechanism
- [ ] Revocation capability
- [ ] No sensitive data in payload

Phase 6: API Security

Rate Limiting

- [ ] Enabled on all endpoints
- [ ] Stricter on auth endpoints
- [ ] Per-user and per-IP
- [ ] Graduated response

CORS

// Secure configuration
{
  origin: ['https://app.example.com'],  // Not '*'
  credentials: true,
  methods: ['GET', 'POST', 'PUT', 'DELETE']
}

Error Handling

- [ ] Generic messages to clients
- [ ] Details in logs only
- [ ] No stack traces in production
- [ ] Consistent format

Phase 7: Report & Remediation

Report Template

# Security Audit Report

**Date**: YYYY-MM-DD
**Auditor**: [Name]
**Scope**: [Full/Focused/Quick]
**Duration**: [Hours]

## Executive Summary

| Severity | Count | Status |
|----------|-------|--------|
| Critical | N | [Status] |
| High | N | [Status] |
| Medium | N | [Status] |
| Low | N | [Status] |

**Overall Risk**: [Low/Medium/High/Critical]

## Findings

### [Severity]: [Issue Title]
**Location**: [File:Line]
**Description**: [Brief description]
**Impact**: [Potential impact]
**Remediation**: [How to fix]
**Timeline**: [When to fix]

## Recommendations

1. [Recommendation 1]
2. [Recommendation 2]

## Tools Used

- [Tool 1]
- [Tool 2]

Priority Matrix

FindingSeverityEffortPriority
SQL InjectionCriticalLowImmediate
Missing AuthHighMediumSprint 1
Weak HashHighLowSprint 1
Missing HeadersMediumLowSprint 2
Old DependencyLowLowBacklog

Follow-up

  • Create tickets for findings
  • Schedule remediation
  • Plan re-audit
  • Update documentation
  • Brief team

Quick Scan Commands

# Node.js
npm audit && npx gitleaks detect

# Python
pip-audit && gitleaks detect

# Go
govulncheck ./... && gitleaks detect

# Rust
cargo audit && gitleaks detect

Summary Checklist

OWASP Top 10

  • A01: Broken Access Control
  • A02: Cryptographic Failures
  • A03: Injection
  • A04: Insecure Design
  • A05: Security Misconfiguration
  • A06: Vulnerable Components
  • A07: Authentication Failures
  • A08: Data Integrity Failures
  • A09: Logging Failures
  • A10: SSRF

Core Security

  • Dependencies scanned
  • Secrets detection run
  • Input validation checked
  • Auth/authz reviewed
  • API security validated
  • Security headers set

Additional Resources

Extended Content:

  • references/process.md - Detailed vulnerability patterns, code examples, language-specific guidance

Related Workflows:

  • code-review.md - Includes security checks
  • dependency-update.md - Safe dependency updates
  • troubleshooting.md - Security incident response

Remember: Security is continuous. Integrate automated scanning into CI/CD, conduct regular reviews, and maintain security-first development practices.

平台分布

Codex

33.31%
按下载量换算34

Claude

27.59%
按下载量换算28

Cursor

19.21%
按下载量换算20

Gemini CLI

10.16%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。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