Token导航 LogoToken导航

Agent Skill · 研究检索

security-auditor(安全审计员)

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-auditor 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,权限为需要联网;许可证为 MIT,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 29,254。

总安装 3,089周安装 130GitHub Stars 76下载 1,082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
MIT

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-auditor(安全审计员)
来源仓库:https://github.com/404kidwiz/claude-supercode-skills
仓库路径:skills/security-auditor
安装命令:
npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill security-auditor
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill security-auditor

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-auditor 辅助安全合规审计,覆盖 SOC 2、ISO 27001 等标准评估。可用于自动化证据收集、云安全态势检查与第三方供应商风险审查。提供差距分析与整改清单,但不替代人工最终判断与生产系统操作。

安装方式:npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill security-auditor 处理密钥、令牌或用户数据前务必启用脱敏并限制权限范围,防止泄露风险。

来源仓库内路径:skills/security-auditor

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/404kidwiz/claude-supercode-skills --skill secu…;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

    它需要需要联网,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-auditor 怎么安装?

在终端执行 npx skills add https://github.com/404kidwiz/claude-supercode-skills --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-auditor 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-auditor 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

security-auditor 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

security-auditor 用的人多吗?

公开数据是累计安装 3,089 次,近一周安装 130 次,下载 1,082 次,GitHub 76 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-auditor 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 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

  • 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-auditor

安全审计员 · 本页

3,08976需要联网MIT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 Auditor

Purpose

Provides security compliance and audit expertise specializing in SOC 2, ISO 27001, and regulatory frameworks. Evaluates organizational security posture through automated evidence collection, gap analysis, and audit preparation.

When to Use

  • Preparing for a SOC 2 Type I or Type II audit
  • Aligning infrastructure with ISO 27001 / HIPAA / PCI-DSS standards
  • Automating evidence collection (Drata, Vanta, Secureframe)
  • Conducting a Third-Party Risk Assessment (Vendor Review)
  • Performing a Cloud Security Posture Review (CSPM)
  • Designing internal audit programs

Examples

Example 1: SOC 2 Type II Preparation

Scenario: A SaaS startup preparing for their first SOC 2 Type II audit.

Implementation:

  1. Conducted gap analysis against SOC 2 criteria
  2. Designed and implemented 45 security controls
  3. Automated evidence collection for all criteria
  4. Created comprehensive documentation package
  5. Ran 3 months of observation period

Results:

  • Passed SOC 2 Type II with zero non-conformities
  • Audit duration reduced from 6 months to 3 months
  • Evidence collection automated (90% less manual effort)
  • Customer confidence increased significantly

Example 2: ISO 27001 Implementation

Scenario: An enterprise implementing ISO 27001 for market access.

Implementation:

  1. Conducted risk assessment following ISO methodology
  2. Created Statement of Applicability (SoA)
  3. Implemented 82 controls from Annex A
  4. Established ISMS governance structure
  5. Conducted internal audit and management review

Results:

  • ISO 27001 certification achieved in 8 months
  • Security posture improved across organization
  • Access to new markets requiring certification
  • Insurance premiums reduced by 15%

Example 3: Third-Party Risk Assessment

Scenario: Assessing 100+ vendors for security and compliance.

Implementation:

  1. Developed tiered assessment approach by risk criticality
  2. Created standardized security questionnaire
  3. Implemented continuous monitoring for critical vendors
  4. Established vendor risk scoring methodology
  5. Created remediation tracking and escalation

Results:

  • 100% vendors assessed
  • 12 high-risk vendors requiring remediation
  • Clear risk appetite established for vendors
  • Vendor-related security incidents reduced by 80%

Best Practices

Audit Preparation

  • Early Start: Begin preparation 6+ months before audit
  • Gap Analysis: Understand current state vs. requirements
  • Control Design: Implement controls before trying to operate them
  • Automation: Automate evidence collection where possible

Evidence Management

  • Continuous Collection: Don't wait for audit to collect evidence
  • Centralized Storage: Organized evidence repository
  • 完整性: Ensure evidence accuracy and completeness
  • Accessibility: Easy to retrieve and present

Control Testing

  • Operating Effectiveness: Test that controls work as designed
  • Sample Size: Appropriate sampling methodology
  • Documentation: Clear testing procedures and results
  • Remediation: Track and resolve control deficiencies

Compliance Monitoring

  • Continuous: Monitor compliance, not just at audit time
  • Metrics: Track compliance KPIs
  • Trends: Identify patterns and emerging issues
  • Reporting: Regular compliance status updates


2. Decision Framework

Compliance Framework Selection

What is the business goal?
│
├─ **B2B SaaS Sales?**
│  ├─ US Market? → **SOC 2** (Trust Services Criteria)
│  └─ International? → **ISO 27001** (ISMS)
│
├─ **Regulated Industry?**
│  ├─ Healthcare (US)? → **HIPAA**
│  ├─ Payments? → **PCI-DSS**
│  └─ EU Personal Data? → **GDPR**
│
└─ **Federal/Gov?**
   ├─ US Federal? → **FedRAMP**
   └─ Defense? → **CMMC**

Audit Strategy

TypeFrequencyDepthOutput
Gap AnalysisOnce (Start)High (Design)Remediation Roadmap
Internal AuditQuarterlyMedium (Sampling)Internal Report & CAPA
ContinuousReal-timeHigh (Automated)Dashboard / Alerts
External AuditAnnualHigh (Evidence)Attestation Report

Red Flags → Escalate to security-engineer or legal-advisor:

  • "Just check the box" mentality (Security theater)
  • Storing evidence in personal drives (Chain of custody risk)
  • Falsifying evidence (Fraud)
  • Missing legal basis for data processing (GDPR violation)


3. Core Workflows

Workflow 1: SOC 2 Readiness Assessment

Goal: Identify gaps before the external auditor arrives.

Steps:

  1. Scope Definition

- Define the "System Description". - Identify Trust Services Criteria (TSC): Security (Mandatory), Availability, Confidentiality, Processing Integrity, Privacy.

  1. Control Mapping

- *Control:* "Change Management". - *Evidence Needed:* PRs require approval, CI/CD logs. - *Current State:* "Developers push to main." → GAP.

  1. Remediation Plan

- Task: Enable "Branch Protection" on GitHub. - Task: Implement SSO (Okta/Google Workspace). - Task: Encrypt database at rest (AWS RDS KMS).

  1. Policy Generation

- Draft "Information Security Policy". - Draft "Incident Response Plan". - Draft "Access Control Policy".



Workflow 3: Vendor Risk Assessment

Goal: Approve a new sub-processor (e.g., AI API provider).

Steps:

  1. Intake

- Request: "We want to use OpenAI API." - Data Classification: "Confidential (Customer PII)".

  1. Review

- Request SOC 2 Type II report from vendor. - Review "Bridge Letter" (if report is old). - Review "Exceptions" in the report (Did they fail anything?).

  1. Decision

- Approve: Risks managed. - Mitigate: "Yes, but turn off data retention option." - Reject: "Security posture insufficient for PII."



5. Anti-Patterns & Gotchas

❌ Anti-Pattern 1: "Set and Forget" Compliance

What it looks like:

  • Passing the audit in January.
  • Disabling security controls in February to "move faster".
  • Panicking next December.

Why it fails:

  • Type II audits cover a *period of time* (e.g., Jan 1 - Dec 31).
  • Auditor will ask for samples from July. You will fail.

Correct approach:

  • Continuous Compliance: Treat compliance as a product feature. Monitor daily.

❌ Anti-Pattern 2: Over-Scoping

What it looks like:

  • Including the "Marketing Website" (Wordpress) in the SOC 2 scope for the "Banking App".

Why it fails:

  • Wasted effort securing non-critical assets.
  • Audit becomes expensive and slow.

Correct approach:

  • Network Segmentation: Isolate the CDE (Cardholder Data Environment) or Prod environment. Scope *only* the critical environment.

❌ Anti-Pattern 3: Manual Screenshots

What it looks like:

  • Taking 500 screenshots of Jira tickets to prove "Change Management".

Why it fails:

  • Unmaintainable.
  • Screenshots can be faked.

Correct approach:

  • Export Logs: JSON/CSV exports from systems.
  • Read-only Access: Give the auditor read-only access to the tool (Jira/AWS) to verify themselves.


7. Quality Checklist

Preparation:

  • Scope: Clearly defined (System Description).
  • Controls: Mapped to framework (SOC 2 / ISO).
  • Policies: Reviewed and approved by management in the last 12 months.

Evidence:

  • Completeness: Covers the entire audit period.
  • Accuracy: Generated directly from systems (not manually edited).
  • Organization: Stored in structured folders (e.g., Box/Google Drive/Vanta).

Vendor Risk:

  • Critical Vendors: Reviewed annually.
  • Contracts: DPAs (Data Processing Agreements) signed.

HR Security:

  • Onboarding: Background checks completed (where legal).
  • Offboarding: Access revoked within SLA (e.g., 24 hours).

Anti-Patterns

Audit Process Anti-Patterns

  • Point-in-Time Snapshot: Assessing controls only at audit time - continuous monitoring
  • Evidence Fabrication: Creating evidence rather than demonstrating controls - build real compliance
  • Scope Shrinking: Minimizing audit scope to reduce findings - address root causes
  • Checkbox Mentality: Treating compliance as form-filling - focus on security outcomes

Evidence Anti-Patterns

  • Last Minute Rush: Collecting evidence only when auditors arrive - automate evidence collection
  • Incomplete Evidence: Partial evidence raising more questions - comprehensive documentation
  • Outdated Evidence: Using evidence from old systems - maintain current evidence
  • Inaccessible Evidence: Evidence that can't be located - organize and index systematically

Control Assessment Anti-Patterns

  • Paper Controls: Policies only in documentation - implement technical enforcement
  • Over-Complex Controls: Controls too complex to operate - balance security and operability
  • Control Gaps: Leaving security domains uncovered - comprehensive control coverage
  • Control Redundancy: Overlapping controls without coordination - rationalize control portfolio

Remediation Anti-Patterns

  • Temporary Fixes: Bandages instead of permanent solutions - implement root cause fixes
  • Finding Chasing: Prioritizing by audit severity not risk - assess actual business risk
  • Remediation Debt: Accumulated findings without resolution - maintain remediation backlog
  • Siloed Remediation: Fixing in isolation without systemic improvement - prevent recurrence

平台分布

Claude Code

32.39%
按下载量换算350

OpenCode

22.4%
按下载量换算242

Codex

17.49%
按下载量换算189

Cursor

13.26%
按下载量换算143

Gemini CLI

9.08%
按下载量换算98

windsurf

3.57%
按下载量换算39

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

继续浏览同类 Skills