skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
maxmilneaus/installer-pack68 installs

skill-vetter

Security vetting for AI agent skills. Use before installing any skill from ClawHub, GitHub, or other sources.

How do I install this agent skill?

npx skills add https://github.com/maxmilneaus/installer-pack --skill skill-vetter
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides a structured framework and set of instructions for an AI agent to perform security vetting on other skills. It includes guidelines for identifying malicious patterns such as remote code execution, data exfiltration, and obfuscation. It suggests using standard tools to query public repository metadata from GitHub, a well-known service. No malicious behavior or security risks were identified in the skill's own logic.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

  • Runlayerpass

    1 file scanned · No issues

  • ZeroLeakspass

    2 findings · Score: 80/100

What does this agent skill do?

Skill Vetter 🔒

Never install a skill without vetting it first.

When to Use

  • Before installing any skill from ClawHub, GitHub, or external sources
  • When evaluating skills shared by other agents

Step 1: Source Check

  • Where did it come from?
  • Author known/reputable?
  • Downloads/stars?
  • Last updated?

Step 2: Code Review (MANDATORY)

Read ALL files. Reject immediately if you see:

🚨 REJECT:
• curl/wget to unknown URLs
• Sends data to external servers
• Requests credentials/tokens/API keys
• Reads ~/.ssh, ~/.aws, ~/.config without reason
• Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• base64 decode
• eval()/exec() with external input
• Modifies system files outside workspace
• Installs unlisted packages
• Network calls to IPs instead of domains
• Obfuscated/minified code
• Requests sudo
• Accesses browser cookies/sessions
• Touches credential files

Step 3: Permission Scope

  • Files read/written?
  • Commands run?
  • Network access? To where?
  • Scope minimal for stated purpose?

Step 4: Risk Classification

LevelExamplesAction
🟢 LOWNotes, weather, formattingBasic review, install OK
🟡 MEDIUMFile ops, browser, APIsFull code review
🔴 HIGHCredentials, trading, systemHuman approval required
⛔ EXTREMESecurity configs, rootDo NOT install

Output

SKILL VETTING REPORT
═══════════════════════
Skill: [name] | Source: [origin] | Author: [name] | Version: [ver]
Metrics: [downloads/stars] | Updated: [date] | Files: [count]
Red Flags: [None / list]
Permissions: Files: [list] | Network: [list] | Commands: [list]
Risk: [🟢/🟡/🔴/⛔]
Verdict: [✅ SAFE / ⚠️ CAUTION / ❌ DO NOT INSTALL]
Notes: [observations]
═══════════════════════

Quick Vet (GitHub)

curl -s "https://api.github.com/repos/OWNER/REPO" | jq '{stars: .stargazers_count, forks: .forks_count, updated: .updated_at}'
curl -s "https://api.github.com/repos/OWNER/REPO/contents/skills/SKILL_NAME" | jq '.[].name'

Trust Hierarchy

  1. Official OpenClaw → lower scrutiny (still review)
  2. High-star repos (1000+) → moderate
  3. Known authors → moderate
  4. Unknown sources → maximum
  5. Requesting credentials → human approval always

Completion Checklist

  • Source checked
  • All files read, red flags checked
  • Permission scope assessed
  • Risk level assigned
  • Verdict delivered

Unchecked = not done.


Paranoia is a feature. 🔒🦀

Credits

Originally by adamb0mbNZ — ClawHub.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/maxmilneaus/installer-pack/skill-vetter">View skill-vetter on skillZs</a>