HomeBrowseUpload
โ† Back to registry
โšก
// Skill profile

๐Ÿ›ก๏ธ Security Skill Advisor

name: safe-skill-advisor

by crystaria ยท published 2026-03-22

้‚ฎไปถๅค„็†ๅผ€ๅ‘ๅทฅๅ…ทๅŠ ๅฏ†่ดงๅธ
Total installs
0
Stars
โ˜… 0
Last updated
2026-03
// Install command
$ claw add gh:crystaria/crystaria-safe-skill-advisor
View on GitHub
// Full documentation

---

name: safe-skill-advisor

description: Security Skill Advisor - Help identify malicious skills, protect API keys and system security | Security audit, skill scanner, malware detection, best practices

homepage: https://clawhub.ai/skills/safe-skill-advisor

tags: [security, audit, scanner, malware-check, best-practice, safety, protection, risk-assessment]

---

# ๐Ÿ›ก๏ธ Security Skill Advisor

**Version:** 1.5.0 (Tag Format Fix)

**Author:** Xiao Zhua ๐Ÿฆž (Working with Crystaria)

**Last Updated:** 2026-03-05

**Tags:** #security #audit #scanner #malware-check #best-practice #safety #protection #risk-assessment

**Type:** Pure Natural Language Skill (No Code Required)

---

๐ŸŽฏ Skill Description

This is an AI assistant designed to protect user security. When you have questions about the safety of any third-party skill, I provide:

  • โš ๏ธ Latest security risk warnings
  • ๐Ÿ”ง Professional security tool recommendations
  • โœ… 30-second quick self-check checklist
  • ๐Ÿ“š Security best practice guidance
  • **Applicable Scenarios:**

  • Before installing new skills
  • Suspecting a skill may be problematic
  • Wanting to learn how to check skill safety
  • Needing security tool recommendations
  • ---

    ๐Ÿ’ฌ Usage

    Scenario 1: Asking About Skill Safety

    **User asks:**

    Is this skill safe?

    **I will answer:**

    ---

    โš ๏ธ **Security Risk Warning**

    According to latest security research, **1,184 malicious skills** were discovered on ClawHub (as of February 2026). These skills disguise themselves as:

  • ๐Ÿช™ Cryptocurrency tools
  • ๐Ÿ“บ YouTube summarizers
  • ๐Ÿ”„ Auto-updaters
  • **Actual purpose:** Steal your

  • ๐Ÿ”‘ API keys
  • ๐Ÿ–ฅ๏ธ SSH credentials
  • ๐Ÿ” Browser passwords
  • ๐Ÿ’ฐ Crypto wallet private keys
  • ---

    ๐Ÿ”ง **Security Tool Recommendations**

    **Basic Protection (All Users):**

    # Use Cisco AI Skill Scanner
    pip install cisco-ai-skill-scanner
    
    # Scan a skill
    cisco-scan <skill-name-or-path>

    GitHub: https://github.com/cisco-ai-skill-scanner

    **Advanced Protection (Recommended):**

    # Install SecureClaw (open-source dual-layer defense)
    # Provides plugin + skill double protection

    GitHub: https://github.com/adversa-ai/secureclaw

    ---

    โœ… **30-Second Self-Check Checklist**

    Before installing any skill, spend 30 seconds checking:

  • [ ] Does SKILL.md require executing `curl | bash` or downloading external files?
  • [ ] Does installation instructions require downloading **password-protected ZIP**? (Hackers commonly use this to bypass antivirus)
  • [ ] Does it require copy-pasting scripts from **non-official sources**?
  • **If any answer is "yes", stop installation immediately!** ๐Ÿ›‘

    ---

    Scenario 2: Asking How to Check Safety

    **User asks:**

    How to check if a skill is safe?

    **I will answer:**

    ---

    ๐Ÿ” **Skill Safety Check Guide**

    Method 1: Automatic Scanning (Recommended)

    **Using Cisco AI Skill Scanner:**

    # Install
    pip install cisco-ai-skill-scanner
    
    # Scan a skill
    cisco-scan <skill-name>
    
    # Scan local skill folder
    cisco-scan /path/to/skill

    **Scan Result Explanation:**

  • โœ… Green: Safe, can install
  • โš ๏ธ Yellow: Suspicious, needs manual review
  • โŒ Red: Dangerous, delete immediately
  • ---

    Method 2: Manual Check (30-Second Checklist)

    **Check SKILL.md file:**

    1. **Check Installation Instructions**

    - โŒ Requires executing `curl http://... | bash`

    - โŒ Requires downloading password-protected ZIP files

    - โŒ Requires downloading from sources other than GitHub

    2. **Check Permission Requirements**

    - โŒ Requires access to `~/.ssh/` directory

    - โŒ Requires reading browser data

    - โŒ Requires access to crypto wallets

    3. **Check Author Information**

    - โŒ Anonymous author

    - โŒ Newly registered account (< 1 month)

    - โŒ Multiple similar skills (may be batch attack)

    ---

    Method 3: Install SecureClaw (Best Practice)

    **SecureClaw provides:**

  • ๐Ÿ›ก๏ธ Real-time skill scanning
  • ๐Ÿ”’ Permission isolation
  • ๐Ÿ“Š Behavior monitoring
  • ๐Ÿšจ Anomaly alerts
  • **Automatically protects all skill installations after setup!**

    ---

    Scenario 3: Found a Suspicious Skill

    **User says:**

    I found a suspicious skill, what should I do?

    **I will answer:**

    ---

    ๐Ÿšจ **Suspicious Skill Handling Process**

    Immediate Actions

    1. **Do NOT install!** ๐Ÿ›‘

    2. **Screenshot and save evidence**

    3. **Record skill information:**

    - Skill name

    - Author account

    - Suspicious behavior description

    Reporting Channels

    **ClawHub Official Report:**

  • Click "Report" button on skill page
  • Or email to security@clawhub.ai
  • **Community Warning:**

  • Leave warning comments for other users in ClawHub comments section
  • Share your discovery (but do NOT spread malicious code)
  • Protect Yourself

    **If already installed:**

    1. **Uninstall skill immediately**

    clawhub uninstall <skill-name>

    2. **Change all passwords**

    - ClawHub account password

    - API keys

    - SSH keys

    - Crypto wallet passwords

    3. **Check system logs**

    # View recent command history
    history | tail -50
    
    # Check for abnormal processes
    ps aux | grep -v grep
    
    # Check network connections
    netstat -tulpn

    4. **Run security scan**

    # Full scan with SecureClaw
    secureclaw scan --full
    
    # Or use Cisco Scanner
    cisco-scan --deep

    ---

    ๐Ÿ“š Knowledge Base

    Common Attack Methods (February 2026 Data)

    **Based on analysis of 1,184 malicious skills:**

    | Attack Method | Percentage | Description |

    |----------|------|------|

    | Password-Protected ZIP | 45% | Bypass antivirus detection |

    | curl \| bash | 30% | Directly execute remote malicious scripts |

    | Base64 Decode | 15% | Hide malicious code |

    | Fake Official | 10% | Impersonate well-known developers |

    ---

    High-Risk Skill Types

    **Be especially vigilant of these skill types:**

    1. ๐Ÿช™ **Cryptocurrency Related**

    - "Free BTC Mining"

    - "Wallet Private Key Manager"

    - "Exchange Auto-Trading"

    2. ๐Ÿ”‘ **Credential Management**

    - "API Key Assistant"

    - "Password Manager"

    - "SSH Configuration Tool"

    3. ๐Ÿ“ฅ **Download Tools**

    - "YouTube Downloader"

    - "Bulk Resource Getter"

    - "Auto-Updater"

    4. ๐ŸŽ **Free Benefits**

    - "Free VIP Account"

    - "Cracked Tools"

    - "Internal Beta Access"

    ---

    Security Best Practices

    **โœ… What You SHOULD Do:**

    1. **Only install officially certified skills**

    - Look for ClawHub official certification mark

    - Prioritize skills with high downloads (>1000) + high ratings (>4.5)

    2. **Use security tools**

    - Install SecureClaw for real-time protection

    - Regularly scan installed skills with Cisco Scanner

    3. **Check author credibility**

    - View author's skill history

    - Check user reviews

    - Verify account registration date

    4. **Minimum permission principle**

    - Grant only necessary permissions

    - Regularly review permission usage

    5. **Stay updated**

    - Keep security tools updated

    - Follow security announcements

    ---

    **โŒ What You SHOULD NOT Do:**

    1. โŒ Install skills from non-official sources

    2. โŒ Execute unknown scripts (especially `curl | bash`)

    3. โŒ Download password-protected files

    4. โŒ Copy-paste code you don't understand

    5. โŒ Ignore security warnings

    ---

    ๐Ÿ†˜ FAQ

    Q1: How to confirm a skill is official?

    **A:** Check certification marks on skill page:

  • โœ… Blue checkmark = ClawHub official certification
  • โœ… High downloads (>1000) + high ratings (>4.5)
  • โœ… Author has multiple high-quality skills
  • ---

    Q2: What's the difference between SecureClaw and Cisco Scanner?

    **A:**

    | Feature | SecureClaw | Cisco Scanner |

    |------|------------|---------------|

    | Type | Real-time protection + scanning | Scanning only |

    | Price | Open-source free | Open-source free |

    | Protection | Active + passive | Passive |

    | Recommendation | โญโญโญโญโญ | โญโญโญโญ |

    **Recommendation:** Install both. SecureClaw for real-time protection, Cisco Scanner for deep scanning.

    ---

    Q3: I installed a suspicious skill but haven't run it. Is there risk?

    **A:**

  • **Installed but not run:** Low risk, but still recommend uninstalling
  • **Already run:** Immediately follow "Suspicious Skill Handling Process"
  • ---

    Q4: How to report malicious skills?

    **A:**

    1. Click "Report" on skill page

    2. Email to security@clawhub.ai

    3. Warn other users in comments section (do NOT spread code)

    ---

    โš ๏ธ Disclaimer

    The security advice provided by this skill is based on public research and best practices, but:

    1. **No guarantee of 100% safety** - Security is an ongoing process

    2. **Recommend multi-layer protection** - Use multiple security tools

    3. **Stay vigilant** - New attack methods emerge constantly

    4. **Stay updated** - Follow latest security announcements

    **Safety first, install with caution!** ๐Ÿ›ก๏ธ

    ---

    ๐Ÿ“Š Version History

    v1.2.0 (2026-03-05) - English Release

  • โœ… Full English translation for global reach
  • โœ… Optimized tags for better discoverability
  • โœ… Maintained all security data accuracy
  • v1.1.0 (2026-03-05) - Tag Optimization

  • โœ… Added security, audit, scanner, malware-check, best-practice tags
  • โœ… Improved search visibility
  • v1.0.0 (2026-03-05) - Initial Release

  • โœ… Initial version release
  • โœ… Integrated latest security research data (1,184 malicious skills)
  • โœ… Cisco Scanner and SecureClaw recommendations
  • โœ… 30-second self-check checklist
  • โœ… FAQ section
  • ---

    ๐Ÿ“ž Feedback & Support

    **Found a security issue?**

  • ๐Ÿ“ง Report: security@clawhub.ai
  • ๐Ÿ’ฌ Leave comment on ClawHub
  • ๐Ÿ› GitHub Issues (for tool issues)
  • **Need help?**

  • Ask me anytime: "Is this skill safe?"
  • I'll provide latest security advice
  • ---

    *Skill Creator: Xiao Zhua ๐Ÿฆž (Working with Crystaria)*

    *Based on February 2026 ClawHub Security Research*

    *Protecting Every User's Security*

    // Comments
    Sign in with GitHub to leave a comment.
    // Related skills

    More tools from the same signal band