S

Secucheck

secucheck

Comprehensive security audit for OpenClaw. Scans 7 domains (runtime, channels, agents, cron, skills, sessions, network), supports 3 expertise levels, context-aware analysis, and visual dashboard. Read-only with localized reports.

数据来源：ClawHub。在 ClawSkills 查看

3.1k下载量

4收藏数

3浏览量

安装

选择你使用的 Agent

方法一：命令行安装（推荐）

关于 Secucheck

--- name: secucheck description: Comprehensive security audit for OpenClaw. Scans 7 domains (runtime, channels, agents, cron, skills, sessions, network), supports 3 expertise levels, context-aware analysis, and visual dashboard. Read-only with localized reports. tags: [security, audit, hardening, runtime, dashboard, prompt-injection] ---

secucheck - OpenClaw Security Audit

Comprehensive security audit skill for OpenClaw deployments. Analyzes configuration, permissions, exposure risks, and runtime environment with context-aware recommendations.

---

Summary

secucheck performs read-only security audits of your OpenClaw setup:

7 audit domains: Runtime, Channels, Agents, Cron Jobs, Skills, Sessions, Network
3 expertise levels: Beginner (analogies), Intermediate (technical), Expert (attack vectors)
Context-aware: Considers VPN, single-user, self-hosted scenarios
Runtime checks: Live system state (network exposure, containers, privileges)
Dashboard: Visual HTML report with security score
Localized output: Final report matches user's language

Never modifies configuration automatically. All fixes require explicit user confirmation.

---

Quick Start

Installation

clawhub install secucheck

Usage

Ask your OpenClaw agent:

"security audit"
"secucheck"
"run security check"

Expertise Levels

When prompted, choose your level:

Beginner - Simple analogies, no jargon
Intermediate - Technical details, config examples
Expert - Attack vectors, edge cases, CVEs

All levels run the same checks—only explanation depth varies.

Dashboard

"show dashboard" / "visual report"

Opens an HTML report in your browser.

---

Example Output

🔒 Security Audit Results

🟡 Needs Attention

| Severity | Count |
|----------|-------|
| 🔴 Critical | 0 |
| 🟠 High | 0 |
| 🟡 Medium | 2 |
| 🟢 Low | 3 |

### 🟡 Agent "molty": exec + external content processing
...

---

Features

🔍 Comprehensive: Channels, agents, cron, skills, sessions, network, runtime
👤 3 Expertise Levels: Beginner / Intermediate / Expert
🌏 Localized: Final report in user's language
🎯 Attack Scenarios: Real-world exploitation paths
⚡ Runtime Checks: VPN, containers, privileges, network exposure
🎨 Dashboard: Visual HTML report with security score

---

Agent Instructions

Everything below is for the agent executing this skill.

---

When to Use

Trigger this skill when:

User requests security checkup/audit
Auto-trigger: Installing skills, creating/modifying agents, adding/modifying cron jobs
Periodic review (recommended: weekly)

Expertise Levels

| Level | Identifier | Style | |-------|------------|-------| | Beginner | 1, beginner | Analogies, simple explanations, no jargon | | Intermediate | 2, intermediate | Technical details, config examples | | Expert | 3, expert | Attack vectors, edge cases, CVE references |

Execution Flow

Step 1: Ask Level (before running anything)

Present options in user's language. Example (English):

What level of technical detail do you prefer?

1. 🌱 Beginner - I'll explain simply with analogies
2. 💻 Intermediate - Technical details and config examples
3. 🔐 Expert - Include attack vectors and edge cases

📌 All levels run the same checks—only explanation depth varies.

STOP HERE. Wait for user response.

Step 2: Run Audit

bash ~/.openclaw/skills/secucheck/scripts/full_audit.sh

Returns JSON with findings categorized by severity.

Step 3: Format Output

Parse JSON output and format based on user's expertise level. Final report must be in user's language.

Report Structure (Organize by Category)

🔒 Security Audit Results

📊 Summary Table
| Severity | Count |
|----------|-------|
| 🔴 Critical | X |
| ...

⚡ Runtime
- [findings related to RUNTIME category]

🤖 Agents  
- [findings related to AGENT category]

📁 Workspace
- [findings related to WORKSPACE category]

🧩 Skills
- [findings related to SKILL category]

📢 Channels
- [findings related to CHANNEL category]

🌐 Network
- [findings related to NETWORK category]

Group findings by their category field, not just severity. Within each category, show severity icon and explain.

Step 4: Auto-Open Dashboard

After text report, automatically generate and serve dashboard:

bash ~/.openclaw/skills/secucheck/scripts/serve_dashboard.sh

The script returns JSON with url (LAN IP) and local_url (localhost). Use the url field (not localhost) when telling the user — they may access from another device.

Example:

📊 대시보드도 열었어요: http://192.168.1.200:8766/secucheck-report.html

If running in environment where browser can be opened, use browser tool to open it.

Cross-Platform Support

Scripts run on Linux, macOS, and WSL. Check the JSON output for platform info:

{
  "os": "linux",
  "os_variant": "ubuntu",
  "in_wsl": false,
  "in_dsm": false,
  "failed_checks": ["external_ip"]
}

Platform Detection

| Field | Values | |-------|--------| | os | linux, macos, windows, unknown | | os_variant | ubuntu, arch, dsm, wsl, version string | | in_wsl | true if Windows Subsystem for Linux | | in_dsm | true if Synology DSM |

Handling Failed Checks

If failed_checks array is non-empty, run fallback commands based on platform:

Network Info Fallbacks

| Platform | Command | |----------|---------| | Linux | ip addr show or ifconfig | | macOS | ifconfig | | WSL | ip addr show (or check Windows via cmd.exe /c ipconfig) | | Windows | PowerShell: Get-NetIPAddress | | DSM | ifconfig or /sbin/ip addr |

Gateway Binding Fallbacks

| Platform | Command | |----------|---------| | Linux | ss -tlnp \| grep :18789 or netstat -tlnp | | macOS | lsof -iTCP:18789 -sTCP:LISTEN | | Windows | PowerShell: Get-NetTCPConnection -LocalPort 18789 |

File Permissions Fallbacks

| Platform | Command | |----------|---------| | Linux/macOS | ls -la ~/.openclaw | | Windows | PowerShell: Get-Acl $env:USERPROFILE\.openclaw |

Windows Native Support

If os is windows and scripts fail completely:

Use PowerShell commands directly:

# Network exposure
Get-NetTCPConnection -LocalPort 18789 -State Listen

# File permissions
Get-Acl "$env:USERPROFILE\.openclaw"

# Process info
Get-Process | Where-Object {$_.Name -like "*openclaw*"}

Report what you can check and note Windows-specific limitations.

Minimal Environments (Docker, DSM)

Some environments lack tools. Check output and supplement:

| Missing Tool | Fallback | |--------------|----------| | curl | wget -qO- | | ss | netstat | | ip | ifconfig or /sbin/ip | | pgrep | ps aux \| grep |

Agent Decision Flow

1. Run full_audit.sh
2. Check "failed_checks" in output
3. For each failed check:
   a. Identify platform from os/os_variant
   b. Run platform-specific fallback command
   c. Incorporate results into report
4. Note any checks that couldn't complete

Dashboard Generation

When user requests visual report:

bash ~/.openclaw/skills/secucheck/scripts/serve_dashboard.sh

Returns:

{
  "status": "ok",
  "url": "http://localhost:8766/secucheck-report.html",
  "pid": 12345
}

Provide URL directly to user.

Detailed Check References

Read these only when deep explanation needed:

| File | Domain | |------|--------| | checks/runtime.md | Live system state | | checks/channels.md | Channel policies | | checks/agents.md | Agent permissions | | checks/cron.md | Scheduled jobs | | checks/skills.md | Installed skills | | checks/sessions.md | Session isolation | | checks/network.md | Network configuration |

Attack Scenario Templates

Use these for expert-level explanations:

...

Prompt 示例

安装 Secucheck 后，可以对 AI 说这些话来触发它

U

Help me get started with Secucheck

A

Explains what Secucheck does, walks through the setup, and runs a quick demo based on your current project

U

Use Secucheck to comprehensive security audit for OpenClaw

A

Invokes Secucheck with the right parameters and returns the result directly in the conversation

U

What can I do with Secucheck in my marketing & growth workflow?

A

Lists the top use cases for Secucheck, with example commands for each scenario

常见问题

如何安装 Secucheck？▾

将技能文件夹放到 ~/.claude/skills/secucheck/ 目录（个人级，所有项目可用），或 .claude/skills/secucheck/（项目级）。重启 AI 客户端后，用 /secucheck 主动调用，或让 AI 根据上下文自动发现并使用。

Secucheck 支持哪些 AI 平台？▾

Secucheck 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。

Secucheck 是免费的吗？▾

Secucheck 可免费安装使用。请查阅仓库了解许可证信息。

Secucheck 有什么功能？▾

Comprehensive security audit for OpenClaw. Scans 7 domains (runtime, channels, agents, cron, skills, sessions, network), supports 3 expertise levels, context-aware analysis, and visual dashboard. Read-only with localized reports.

Secucheck 属于哪个分类？▾

Secucheck 属于「Marketing & Growth」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。

使用场景

Getting Started with Secucheck→Automate Marketing & Growth Workflows with Secucheck→Team Collaboration with Secucheck→

Secucheck

安装

关于 Secucheck

secucheck - OpenClaw Security Audit

Summary

Quick Start

Installation

Usage

Expertise Levels

Dashboard

Example Output

Features

Agent Instructions

When to Use

Expertise Levels

Execution Flow

Step 1: Ask Level (before running anything)

Step 2: Run Audit

Step 3: Format Output

Report Structure (Organize by Category)

Step 4: Auto-Open Dashboard

Cross-Platform Support

Platform Detection

Handling Failed Checks

Network Info Fallbacks

Gateway Binding Fallbacks

File Permissions Fallbacks

Windows Native Support

Minimal Environments (Docker, DSM)

Agent Decision Flow

Dashboard Generation

Detailed Check References

Attack Scenario Templates

Prompt 示例

常见问题

使用场景

同类技能推荐

AdMapix

API Gateway

Mcporter

Discord