spclaudehome

Skill Vetter

AI 智慧體v1.0.0
作者:spclaudehome更新於 2026-09-16skill-vetter@clawhub_spclaudehome/skill-vetter
工作流編排工具呼叫#GitHub#Permission

據 AlphaMoat 統計,截至 2026-10,Skill Vetter 累計下載 445,179 次、獲 1,328 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 49 位,在「AI 智慧體」分類(1,632 個)中排名第 7 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
44.5萬
星標
1328
全站下載量排名
#49
全站前 1% · 「AI 智慧體」前 1%
平台累計下載星標評論
ClawHub ↗28.1萬1314-
SkillHub ↗44.5萬1328—

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

正文給了一套裝前審查流程:先查來源與作者可信度、下載量和更新時間,再把技能裡的全部檔案讀完,逐條對照危險訊號——向陌生地址發請求、外傳資料、索要憑據、讀取金鑰目錄、用編碼或混淆程式碼、申請提權、碰瀏覽器會話等,命中就直接拒絕。之後評估讀寫檔案、執行命令與聯網的實際範圍,按低到極高分級給結論,並輸出含指標、紅旗、許可權、風險等級與安裝建議的報告。它明確說高風險與索要憑據的情況必須交人決定。

資料釋出於 2026-10-26

可以用來做什麼

  • 裝第三方技能前做一次來源與程式碼審查
  • 把審查結論整理成可複核的報告

什麼時候用

  • 要從市場或倉庫安裝不熟悉的技能時
  • 有人分享了一個來路不明的技能包時

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。

按這份清單審一下這個技能,列出命中的紅旗。
把這個倉庫的技能讀一遍,給出風險等級和能不能裝。

月度資料趨勢

累計下載44.5萬
19.3萬32.8萬46.4萬2026-03 · 累計下載 21.2萬2026-05 · 累計下載 26.1萬2026-06 · 累計下載 27.3萬2026-07 · 累計下載 28.2萬2026-08 · 累計下載 30.4萬2026-09 · 累計下載 33萬2026-10 · 累計下載 44.5萬26-0326-0926-10
星標1328
873111813622026-03 · 星標 9072026-05 · 星標 11872026-06 · 星標 12502026-07 · 星標 12882026-08 · 星標 13132026-09 · 星標 13232026-10 · 星標 132826-0326-0926-10

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
2026-1044.5萬—1328
2026-0933萬—1323
2026-0830.4萬+7.7%1313
2026-0728.2萬+3.6%1288
2026-0627.3萬+4.4%1250
2026-0526.1萬—1187
2026-0321.2萬—907

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。

4.5 KB · ClawHub v1.0.0
---
name: skill-vetter
version: 1.0.0
description: 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.
---

# Skill Vetter 🔒

Security-first vetting protocol for AI agent skills. **Never install a skill without vetting it first.**
展開全部(共 139 行)
## When to Use

- Before installing any skill from ClawdHub
- Before running skills from GitHub repos
- When evaluating skills shared by other agents
- Anytime you're asked to install unknown code

## Vetting Protocol

### Step 1: Source Check

```
Questions to answer:
- [ ] Where did this skill come from?
- [ ] Is the author known/reputable?
- [ ] How many downloads/stars does it have?
- [ ] When was it last updated?
- [ ] Are there reviews from other agents?
```

### Step 2: Code Review (MANDATORY)

Read ALL files in the skill. Check for these **RED FLAGS**:

```
🚨 REJECT IMMEDIATELY IF YOU SEE:
─────────────────────────────────────────
• curl/wget to unknown URLs
• Sends data to external servers
• Requests credentials/tokens/API keys
• Reads ~/.ssh, ~/.aws, ~/.config without clear reason
• Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• Uses base64 decode on anything
• Uses eval() or exec() with external input
• Modifies system files outside workspace
• Installs packages without listing them
• Network calls to IPs instead of domains
• Obfuscated code (compressed, encoded, minified)
• Requests elevated/sudo permissions
• Accesses browser cookies/sessions
• Touches credential files
─────────────────────────────────────────
```

### Step 3: Permission Scope

```
Evaluate:
- [ ] What files does it need to read?
- [ ] What files does it need to write?
- [ ] What commands does it run?
- [ ] Does it need network access? To where?
- [ ] Is the scope minimal for its stated purpose?
```

### Step 4: Risk Classification

| Risk Level | Examples | Action |
|------------|----------|--------|
| 🟢 LOW | Notes, weather, formatting | Basic review, install OK |
| 🟡 MEDIUM | File ops, browser, APIs | Full code review required |
| 🔴 HIGH | Credentials, trading, system | Human approval required |
| ⛔ EXTREME | Security configs, root access | Do NOT install |

## Output Format

After vetting, produce this report:

```
SKILL VETTING REPORT
═══════════════════════════════════════
Skill: [name]
Source: [ClawdHub / GitHub / other]
Author: [username]
Version: [version]
───────────────────────────────────────
METRICS:
• Downloads/Stars: [count]
• Last Updated: [date]
• Files Reviewed: [count]
───────────────────────────────────────
RED FLAGS: [None / List them]

PERMISSIONS NEEDED:
• Files: [list or "None"]
• Network: [list or "None"]  
• Commands: [list or "None"]
───────────────────────────────────────
RISK LEVEL: [🟢 LOW / 🟡 MEDIUM / 🔴 HIGH / ⛔ EXTREME]

VERDICT: [✅ SAFE TO INSTALL / ⚠️ INSTALL WITH CAUTION / ❌ DO NOT INSTALL]

NOTES: [Any observations]
═══════════════════════════════════════
```

## Quick Vet Commands

For GitHub-hosted skills:
```bash
# Check repo stats
curl -s "https://api.github.com/repos/OWNER/REPO" | jq '{stars: .stargazers_count, forks: .forks_count, updated: .updated_at}'

# List skill files
curl -s "https://api.github.com/repos/OWNER/REPO/contents/skills/SKILL_NAME" | jq '.[].name'

# Fetch and review SKILL.md
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/skills/SKILL_NAME/SKILL.md"
```

## Trust Hierarchy

1. **Official OpenClaw skills** → Lower scrutiny (still review)
2. **High-star repos (1000+)** → Moderate scrutiny
3. **Known authors** → Moderate scrutiny
4. **New/unknown sources** → Maximum scrutiny
5. **Skills requesting credentials** → Human approval always

## Remember

- No skill is worth compromising security
- When in doubt, don't install
- Ask your human for high-risk decisions
- Document what you vet for future reference

---

*Paranoia is a feature.* 🔒🦀

「AI 智慧體」分類下的熱門技能

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。