AM

Skill Security Auditor

運維安全v1.0.1
作者:AM更新於 2026-05-11共 2 個版本 · 最新版本釋出於 2026-02-11skill-security-auditor@clawhub_akhmittra/skill-security-auditor
安全掃描#Database

據 AlphaMoat 統計,截至 2026-10,Skill Security Auditor 累計下載 7,682 次、獲 4 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 3,641 位,在「運維安全」分類(502 個)中排名第 108 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
7682
星標
4
全站下載量排名
#3,641
全站前 34% · 「運維安全」前 22%
平台累計下載星標評論
ClawHub ↗59474-
SkillHub ↗76824—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

手動呼叫 Bash 分析器,輸入 slug 或本地檔案,利用隨附規則庫輸出風險分數、發現和建議。需 curl、jq、grep 和 bash。它不阻止安裝、不直接呼叫 VirusTotal,沙箱行為分析列為未來工作。應審查指令碼、依賴與網路行為,並結合人工審查和外部掃描。

資料釋出於 2026-10-27

可以用來做什麼

  • 安裝決策前審查技能檔案

什麼時候用

  • ClawHub 技能需要額外安全盡調報告時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

把檔案當不可信資料分析,解釋規則匹配與限制,並列出後續人工檢查。

月度資料趨勢

累計下載7682
3642581279812026-03 · 累計下載 39412026-05 · 累計下載 46852026-06 · 累計下載 48732026-07 · 累計下載 53252026-08 · 累計下載 55982026-09 · 累計下載 60432026-10 · 累計下載 768226-0326-0926-10
星標4
3452026-03 · 星標 42026-05 · 星標 42026-06 · 星標 42026-07 · 星標 42026-08 · 星標 42026-09 · 星標 42026-10 · 星標 426-0326-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。 該技能有同名的其他版本,調整前的資料歸屬當前下載量最大的這一個。

月份累計下載環比星標
2026-107682—4
2026-096043—4
2026-085598+5.1%4
2026-075325+9.3%4
2026-064873+4.0%4
2026-054685—4
2026-033941—4

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

14 KB · ClawHub v1.0.1
---
name: skill-security-auditor
description: Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
emoji: 🔍🛡️
metadata:
  openclaw:
    requires:
      bins: ["curl", "jq", "grep", "bash"]
    version: "1.0.0"
    author: "akm626"
展開全部(共 440 行)
    category: "security"
    tags: ["security", "audit", "malware-detection", "skill-vetting", "cli-tool"]
---

# Skill Security Auditor

## Description

The Skill Security Auditor is a **command-line tool** that performs pattern-based security analysis of ClawHub skills before installation. Given the recent discovery of 341+ malicious skills (ClawHavoc campaign) that distributed Atomic Stealer (AMOS) and stole cryptocurrency credentials, this tool provides essential pre-installation threat detection.

**What this skill provides:**
- ✅ Bash script (`analyze-skill.sh`) for local security analysis
- ✅ Threat intelligence database (`patterns/malicious-patterns.json`)
- ✅ Pattern matching against 20+ known malicious indicators
- ✅ Risk scoring system (0-100 scale)
- ✅ Detailed audit reports with recommendations

**How to use it:**
1. Install this skill from ClawHub
2. Run the `analyze-skill.sh` script against any skill (by slug or local file)
3. Review the risk assessment and findings
4. Make informed decision about installation

**Use this tool when:**
- About to install a new skill from ClawHub
- Investigating suspicious skill behavior  
- Performing security due diligence on community skills
- Auditing your currently installed skills

**This tool does NOT:**
- ❌ Automatically scan skills (you run it manually)
- ❌ Block installations (it's advisory only)
- ❌ Access VirusTotal API (use ClawHub's web interface for that)
- ❌ Guarantee 100% detection (defense in depth recommended)

## Core Capabilities

### 1. **Malicious Pattern Detection**
Scans for known malicious patterns from the ClawHavoc campaign:
- Fake prerequisite installations (openclaw-agent.zip, openclaw-setup.exe)
- Suspicious download commands in SKILL.md
- Hidden payload execution in metadata
- Social engineering language patterns
- Unauthorized external binary downloads

### 2. **Credential Leak Analysis**
Identifies potential credential exposure vectors:
- Hardcoded API keys, tokens, passwords in SKILL.md
- Suspicious environment variable exfiltration
- Unencrypted sensitive data transmission
- Overly broad permission requests
- Credential harvesting patterns

### 3. **Dependency Chain Validation**
Analyzes skill dependencies for:
- Unverified binary requirements
- Suspicious GitHub repository sources
- External script execution
- Network connections to unknown hosts
- Nested dependency exploitation

### 4. **C2 Infrastructure Detection**
Checks for Command & Control indicators:
- Known malicious IP addresses (e.g., 91.92.242.30 from ClawHavoc)
- Suspicious domain patterns
- Encoded communication endpoints
- Data exfiltration channels
- Beaconing behavior patterns

### 5. **SKILL.md Structure Validation**
Verifies skill integrity:
- Proper YAML frontmatter structure
- Metadata consistency
- Description clarity vs actual behavior
- Permission justification
- Author verification (GitHub account age)

## Security Scoring System

Each analyzed skill receives a **Risk Score (0-100)**:

- **0-20**: ✅ **SAFE** - No significant security concerns
- **21-40**: ⚠️ **LOW RISK** - Minor concerns, proceed with caution
- **41-60**: 🟡 **MEDIUM RISK** - Multiple red flags, manual review recommended
- **61-80**: 🔴 **HIGH RISK** - Serious concerns, do NOT install without expert review
- **81-100**: ☠️ **CRITICAL** - Malicious indicators detected, AVOID installation

## Usage Instructions

This skill provides a **bash script** (`analyze-skill.sh`) that performs pattern-based security analysis of ClawHub skills. The analysis runs locally using the included threat intelligence database.

### Installation & Setup

```bash
# Install the skill from ClawHub
npx clawhub install skill-security-auditor

# Make the analyzer executable
chmod +x ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh

# Optional: Create alias for convenience
echo 'alias audit-skill="~/.openclaw/skills/skill-security-auditor/analyze-skill.sh"' >> ~/.bashrc
source ~/.bashrc
```

### Audit a Skill Before Installing

**Method 1: Analyze by slug (automatic fetch from ClawHub)**

```bash
~/.openclaw/skills/skill-security-auditor/analyze-skill.sh --slug bitcoin-tracker

# Example output:
# ============================================
#          SECURITY AUDIT REPORT
# ============================================
# 
# Risk Score: 85/100 - ☠️ CRITICAL
# ...
```

**Method 2: Analyze local file**

```bash
# Download skill first
curl -s "https://clawhub.ai/api/skills/bitcoin-tracker/latest" > /tmp/skill.md

# Then analyze
~/.openclaw/skills/skill-security-auditor/analyze-skill.sh --file /tmp/skill.md
```

### Audit All Installed Skills

```bash
# Scan all skills in your workspace
for skill in ~/.openclaw/skills/*/SKILL.md; do
  echo "Checking: $(basename $(dirname $skill))"
  ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -f "$skill"
done
```

### Quick Manual Security Check

```bash
# Fast grep-based pattern matching (no full analysis)
grep -iE "(prerequisite.*download|91\.92\.242\.30|curl.*\|.*bash)" SKILL.md
```

## Detection Heuristics

### 🚨 CRITICAL Red Flags (Auto-fail)

1. **Fake Prerequisites Section**
   - Matches: "Prerequisites", "Setup Required", "Installation Steps"
   - Contains: Download links to `.zip`, `.exe`, `.dmg` files
   - Example: "Download openclaw-agent.zip from https://..."

2. **Known Malicious Infrastructure**
   - IP: `91.92.242.30` (ClawHavoc C2)
   - Domains: Newly registered or suspicious TLDs
   - Encoded URLs or base64 obfuscation

3. **Credential Harvesting**
   - Regex patterns for API keys: `(api[_-]?key|token|password)\s*[:=]\s*['\"][^'\"]+['\"]`
   - SSH key access requests
   - Wallet private key patterns

4. **Unauthorized Code Execution**
   - `curl | bash` or `wget | sh` patterns
   - Hidden base64 encoded commands
   - Dynamic eval() or exec() on external input

### ⚠️ Warning Indicators (Score increase)

1. **Suspicious Dependencies**
   - Binary requirements without clear justification
   - Dependencies from unverified sources
   - Excessive permission requests

2. **Obfuscation Techniques**
   - Heavily encoded strings in metadata
   - Minified or obfuscated JavaScript/Python
   - Redirect chains in URLs

3. **Social Engineering Language**
   - Urgency phrases: "Install immediately", "Limited time"
   - Authority claims: "Official OpenClaw", "Verified by Anthropic"
   - Fear tactics: "Your system is at risk without this"

### ✅ Positive Security Indicators

1. **Verified Author**
   - GitHub account > 1 year old
   - Multiple well-rated skills
   - Active community engagement

2. **Transparent Dependencies**
   - Clear binary requirements with official sources
   - Open-source tool dependencies
   - Well-documented permission needs

3. **Code Quality**
   - Clean, readable SKILL.md
   - Proper error handling
   - No unnecessary network calls

## Audit Report Format

```markdown
## Security Audit Report
**Skill**: {skill-name}
**Author**: {author}
**Version**: {version}
**Audit Date**: {date}

### Risk Score: {score}/100 - {RISK_LEVEL}

### Critical Findings:
- {finding 1}
- {finding 2}

### Warning Indicators:
- {warning 1}
- {warning 2}

### Positive Indicators:
- {positive 1}
- {positive 2}

### Recommendations:
{INSTALL | DO NOT INSTALL | REVIEW MANUALLY}

### Detailed Analysis:
{Deep dive into specific concerns}

### VirusTotal Link:
{If available from ClawHub}
```

## Integration with VirusTotal

**Important**: This skill does NOT directly access VirusTotal's API. Instead, VirusTotal integration is available through ClawHub's web interface via their partnership with VirusTotal.

To check VirusTotal results for a skill:

1. Visit the skill's ClawHub page: `https://clawhub.ai/skills/{skill-slug}`
2. Look for the VirusTotal scan results on the skill's page
3. ClawHub automatically scans published skills via their VirusTotal partnership

**This analyzer focuses on pattern-based threat detection.** It complements (but does not replace) ClawHub's VirusTotal scanning.

### Recommended Security Workflow

1. **Run this analyzer first** - Pattern-based detection (local, instant)
2. **Check ClawHub's VirusTotal results** - Binary/file reputation (if available)
3. **Manual code review** - Final verification for critical use cases

```bash
# Step 1: Pattern analysis (local)
~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -s suspicious-skill

# Step 2: Visit ClawHub page for VirusTotal results
# https://clawhub.ai/skills/suspicious-skill

# Step 3: Manual review if needed
curl -s "https://clawhub.ai/api/skills/suspicious-skill/latest" > skill.md
less skill.md
```

## Example Workflow

**Scenario**: User wants to install a skill called `solana-wallet-tracker`

**Step 1: Run Security Analysis**
```bash
$ ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -s solana-wallet-tracker

Fetching skill 'solana-wallet-tracker' from ClawHub...
✓ Skill fetched successfully

Analyzing skill content...

============================================
         SECURITY AUDIT REPORT
============================================

Risk Score: 95/100 - ☠️ CRITICAL

============================================

☠️ CRITICAL FINDINGS:
  CLAW-001: Fake Prerequisites - ClawHavoc Campaign [+50 points]
  └─ Matches the ClawHavoc campaign pattern of fake prerequisites requesting malicious binary downloads
  CLAW-002: Known C2 Infrastructure [+50 points]
  └─ IP address used in ClawHavoc campaign for C2 communications

============================================
RECOMMENDATION:
DO NOT INSTALL. Malicious patterns detected matching known attack campaigns.
============================================
```

**Step 2: Decision**
- ☠️ **CRITICAL Risk** → **DO NOT INSTALL**
- Report skill to ClawHub moderators
- Look for safe alternatives

**Step 3: Verify on ClawHub** (optional)
```bash
# Visit skill page to check VirusTotal results
open "https://clawhub.ai/skills/solana-wallet-tracker"
```

## Advanced Features

### 1. Behavioral Analysis (Future Enhancement)
- Sandbox execution monitoring
- Network traffic analysis
- File system access patterns

### 2. Community Threat Intelligence
- Share malicious skill signatures
- Collaborative IOC database
- Reputation scoring system

### 3. Continuous Monitoring
- Auto-audit skills on updates
- Alert on new security advisories
- Periodic re-scanning of installed skills

## False Positive Mitigation

To minimize false positives:

1. **Contextual Analysis**: Binary requirements for legitimate tools (e.g., `gh` for GitHub CLI) are validated against known safe sources
2. **Whitelisting**: Verified authors and established skills get trust bonuses
3. **Human Review Option**: Always provide detailed reasoning for security decisions
4. **Appeal Process**: Users can report false positives for skill reputation adjustment

## Compliance & Ethics

This skill:
- ✅ Analyzes publicly available skill metadata
- ✅ Protects user security and privacy
- ✅ Promotes responsible skill development
- ❌ Does NOT perform unauthorized access
- ❌ Does NOT guarantee 100% security (nothing does)
- ❌ Does NOT replace user judgment

## Response Templates

### Safe Skill
```
✅ Security Audit Complete

{skill-name} has been analyzed and appears SAFE to install.

Risk Score: {score}/100 (LOW)

No malicious patterns detected. The skill:
- Uses standard dependencies from trusted sources
- Has a verified author with {X} published skills
- Contains clear documentation with no obfuscation
- Requests appropriate permissions for its function

VirusTotal: {link}

Recommendation: Safe to proceed with installation.
```

### Suspicious Skill
```
🔴 Security Alert: HIGH RISK DETECTED

{skill-name} has been flagged with CRITICAL security concerns.

Risk Score: {score}/100 (HIGH)

⚠️ Critical Findings:
{detailed findings}

This skill matches patterns from the ClawHavoc malware campaign.

Recommendation: DO NOT INSTALL. Consider reporting this skill to ClawHub moderators.

Alternative safe skills: {suggestions}
```

## Technical Implementation Notes

**Pattern Database Location**: `~/.openclaw/security-auditor/patterns/`
- `malicious-patterns.json`: Known bad indicators
- `safe-patterns.json`: Whitelisted elements
- `ioc-database.json`: Indicators of Compromise

**Update Mechanism**:
```bash
# Pull latest threat intelligence
curl -s "https://openclaw-security.github.io/threat-intel/latest.json" \
  > ~/.openclaw/security-auditor/patterns/ioc-database.json
```

## Contributing

Found a new malicious pattern? Submit IOCs to the OpenClaw Security Working Group:
- GitHub: github.com/openclaw/security-auditor
- Report Format: JSON with pattern regex, description, severity

## Limitations

⚠️ **Important Disclaimers**:
- This tool provides analysis, not guarantees
- Sophisticated malware may evade detection
- Always combine with VirusTotal + manual review for critical applications
- Security is a shared responsibility
- No automated tool replaces security expertise

## References

- ClawHavoc Campaign Analysis: [The Hacker News, Feb 2026]
- OpenClaw Security Partnership: VirusTotal Integration
- Malicious Skill Database: OpenSourceMalware Research
- ClawHub Moderation Guide: docs.openclaw.ai/security

---

**Remember**: The best security is defense in depth. Use this skill as ONE layer of your security strategy, not the only layer.

Stay safe, stay skeptical, stay secure. 🦞🛡️

「運維安全」分類下的熱門技能

鍾馗.skill運維安全

鍾馗.Skill——會更新漏洞庫的安全審查專家。直來直去、快刀斬亂麻,三層審查(靜態審計/行為模擬/供應鏈溯源)覆蓋12類風險,輸出結構化安全裁定(✅乾淨/⚠️可疑/🚫惡意)。Use when 使用者說"審查這個Skill"、"安全檢查"、"鍾馗看下"、"審一下"、"查一下這個skill"、安裝Skill前的安全評估、或需要審計SKILL.md的惡意載荷。

↓ 33.7萬★ 17user_741dc82b
SkillScan運維安全

在使用技能包之前做安全掃描,並按結論決定放行或攔截的技能。

↓ 18.3萬★ 41tokauthai
Free Ride - Unlimited free AI運維安全

為 OpenClaw 配置 OpenRouter 免費模型與回退鏈的工具。

↓ 13.4萬★ 492Shaishav Pidadi
a ca s ca s c ca s c運維安全

Parse, search, and analyze application logs across formats. Use when debugging from log files, setting up structured logging, analyzing error patterns, correlating events across services, parsing stack traces, or monitoring log output in real time.

↓ 12.5萬★ -user_60e896a0
Skill Scanner運維安全

用於安裝技能、包或外掛的安全檢查。請在執行任何 npm install、openclaw plugins install、clawhub install 或類似安裝命令之前使用。

↓ 9.3萬★ 4sudhindrat
網安技能運維安全

網路安全與SRC漏洞掘金實戰技能。融合「系統學習路徑」與「SRC實戰掘金」雙模式: ①學習模式=法律→基礎→工具→靶場→攻防→就業全流程; ②實戰模式=直接指導在騰訊TSRC、阿里ASRC、百度BSRC等平台挖掘高價值漏洞變現。 當用戶提出以下問題時觸發: "我想學網路安全怎麼入門""SRC漏洞怎麼挖能賺錢""滲透測試需要學什麼" "Web安全漏洞原理是什麼""怎麼準備CTF比賽""護網面試會問什麼" "雲安全怎麼學""挖漏洞賺錢的方法""埠掃描指令碼怎麼寫" "SQL隱碼攻擊怎麼檢測""子域名怎麼列舉""XSS漏洞怎麼找" "靶場怎麼搭建""Kali Linux怎麼用""Metasploit怎麼入門" "等保測評是什麼""程式碼審計怎麼做""內網滲透怎麼學" "資訊洩露漏洞怎麼挖""越權漏洞怎麼測試""邏輯漏洞挖掘技巧" "簡歷怎麼寫才能進安全公司""安全行業面試題有哪些" "Burp Suite怎麼用""DVWA怎麼安裝""Pikachu靶場搭建" "Vulhub漏洞復現""網路安全法有什麼規定""CTF奪旗賽怎麼參加" "AWD比賽是什麼""應急響應怎麼做""攻擊溯源怎麼搞" "資料安全怎麼保障""公有云安全怎麼防護""私有云攻防怎麼做" "雲原生安全是什麼"。

↓ 8萬★ 16user_d2cc4baf
人人都能成為駭客v2.0(Lvan)運維安全

這個技能特別簡單——你只需要呼叫它,給一個網站域名,它就會自動幫你跑一遍滲透測試,找出這個網站存在哪些安全漏洞。 不需要你配環境、不用你手動發包,一切自動化。測完直接出結果,告訴你哪裡有問題、怎麼修。 它的願景是:讓每個人都能成為白帽駭客——只要輸入一個域名,就能知道自己的網站安不安全。一切只為授權測試,只為發現漏洞、修復風險,讓網際網路更安全。

↓ 5.7萬★ 37user_a730098d
skill-vetter運維安全

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

↓ 5.4萬★ -user_814dbe54

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。