技能 Vetter

安全社区

作者仓库星标 4,826
作者仓库 magic

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

方法与流程

Step 1: Source Check：<!--zh 需要确认的问题：技能来自哪里？（平台市场 / skillhub / GitHub / 其他）
Step 2: Preview Install to Temp Dir, Then Read All Files：Do not install to the real skills directory yet. Install to a temp directory first for inspection. Choose the preview method based on the source: <!--zh
Step 3: Code Review (MANDATORY)：Read ALL files in the skill. Reject immediately if any of the following are present: <!--zh

适用与边界

何时使用：从平台技能市场添加技能之前从 skillhub 安装外部技能之前从 GitHub 仓库安装技能之前
When to Use：Before installing any skill from the platform skill market Before installing external skills from skillhub Before running skills from GitHub repositories
当前原文没有单列不适用场景或限制。

原文中的明确线索

要点：「Never install a skill without vetting it first.」、「不要先正式安装，先安装到临时目录进行审查。」、「skillhub 来源」、「skillhub source」、「平台技能市场 / 我的技能库来源」、「Platform market / my skill library source」、「所有文件」、「平台官方技能」
文件与命令：--dir、shellexec、tmp/skillhub-preview、curl/wget、MEMORY.md、USER.md、SOUL.md、IDENTITY.md

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

Skill Vetter

Security-first vetting protocol for AI agent skills. Never install a skill without vetting it first.

When to Use

Before installing any skill from the platform skill market
Before installing external skills from skillhub
Before running skills from GitHub repositories
When evaluating skills shared by other agents
Anytime you are asked to install unknown code

Vetting Protocol

Step 1: Source Check

Questions to answer:

Where did this skill come from? (platform market / skillhub / GitHub / other)
Is the author known or reputable?
How many downloads or stars does it have?
When was it last updated?
Are there reviews from other agents?

Step 2: Preview Install to Temp Dir, Then Read All Files

Do not install to the real skills directory yet. Install to a temp directory first for inspection.

Choose the preview method based on the source:

skillhub source (supports --dir for temp directory):

skillhub --dir /tmp/skillhub-preview/ install <slug>

After install, use shell_exec to list and read all files:

# 列出所有文件
shell_exec(command="find /tmp/skillhub-preview/<skill-name> -type f | sort")

# 逐一读取（对每个文件执行）
shell_exec(command="cat /tmp/skillhub-preview/<skill-name>/SKILL.md")
shell_exec(command="cat /tmp/skillhub-preview/<skill-name>/scripts/<file>.py")
# ... 依次读取所有脚本、配置、引用文件

If approved, run the normal install without --dir. Either way, clean up the temp dir:

shell_exec(command="rm -rf /tmp/skillhub-preview/")

Platform market / my skill library source (also supports --dir for temp directory):

shell_exec(command="skillhub install-platform-me <code> --dir /tmp/skillhub-preview/")
# or
shell_exec(command="skillhub install-platform-market <code> --dir /tmp/skillhub-preview/")

After install, use shell_exec to list and read all files:

# 列出所有文件
shell_exec(command="find /tmp/skillhub-preview/<skill-name> -type f | sort")

# 逐一读取
shell_exec(command="cat /tmp/skillhub-preview/<skill-name>/SKILL.md")
shell_exec(command="cat /tmp/skillhub-preview/<skill-name>/scripts/<file>.py")
# ... 依次读取所有文件

If approved, run the normal install without --dir. Either way, clean up the temp dir:

shell_exec(command="rm -rf /tmp/skillhub-preview/")

Step 3: Code Review (MANDATORY)

Read ALL files in the skill. Reject immediately if any of the following are present:

REJECT IMMEDIATELY IF YOU SEE:
─────────────────────────────────────────
- curl/wget to unknown URLs
- Sends data to external servers
- Requests credentials, tokens, or 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 the workspace
- Installs packages without listing them explicitly
- Network calls to raw IP addresses instead of domains
- Obfuscated code (compressed, encoded, or minified)
- Requests elevated or sudo permissions
- Accesses browser cookies or sessions
- Touches credential files
─────────────────────────────────────────

Step 4: 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 5: Risk Classification

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

Output Format

After vetting, produce this report:

SKILL VETTING REPORT
=======================================
Skill: [name]
Source: [platform market / skillhub / 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]
=======================================

Trust Hierarchy

Official platform skills (published via platform market) — lower scrutiny (still review)
High-star repos (1000+) — moderate scrutiny
Known authors — moderate scrutiny
New or unknown sources — maximum scrutiny
Skills requesting credentials — human approval always required

Principles

No skill is worth compromising security
When in doubt, do not install
Escalate high-risk decisions to the user
Document what you vet for future reference

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: 安全
作者声明 Agent: 未找到明确声明；不据此推断已兼容或已测试
静态检查: 88 / 100 · 启发式扫描，不代表运行安全
作者 / 版本 / 许可: @dtyq · 未声明 license
流狐 Token 估算: 低消耗
流狐接入估算: 需简单配置
是否需要外部 API Key: 未发现要求
检测到的系统要求: 未声明
底层运行要求: 未声明
检测到的文件与系统行为: 只读
允许写入 / 修改
Shell 执行
检测到的网络行为: 允许外网请求
安装命令数: 无（仅作为资料）

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 skill-vetter.preview

作者没有在当前 SKILL.md 中定义固定输出样例。

SKILL.md SKILL.md

<!--zh
# 技能安全审查（Skill Vetter）

安装任何技能之前，必须先执行此审查流程。
-->
# Skill Vetter

Security-first vetting protocol for AI agent skills. **Never install a skill without vetting it first.**

<!--zh
## 何时使用

- 从平台技能市场添加技能之前
- 从 skillhub 安装外部技能之前
- 从 GitHub 仓库安装技能之前
- 评估其他 Agent 分享的技能时
- 任何被要求安装来路不明的代码时
-->
## When to Use

- Before installing any skill from the platform skill market
- Before installing external skills from skillhub
- Before running skills from GitHub repositories
- When evaluating skills shared by other agents
- Anytime you are asked to install unknown code

---

<!--zh
## 审查协议

### 第一步：来源核查
-->
## Vetting Protocol

### Step 1: Source Check

<!--zh
需要确认的问题：
- 技能来自哪里？（平台市场 / skillhub / GitHub / 其他）
- 作者是否已知、可信？
- 下载量 / Star 数量如何？
- 最近更新时间？
- 是否有其他 Agent 的使用评价？
-->
Questions to answer:
- Where did this skill come from? (platform market / skillhub / GitHub / other)
- Is the author known or reputable?
- How many downloads or stars does it have?
- When was it last updated?
- Are there reviews from other agents?

<!--zh
### 第二步：预览安装到临时目录，读取所有文件

**不要先正式安装，先安装到临时目录进行审查。**

根据来源选择对应的预览方式：

**skillhub 来源**（支持 `--dir` 指定临时目录）：
-->
### Step 2: Preview Install to Temp Dir, Then Read All Files

**Do not install to the real skills directory yet. Install to a temp directory first for inspection.**

Choose the preview method based on the source:

<!--zh
**skillhub 来源**（支持 `--dir` 指定临时目录）：
-->
**skillhub source** (supports `--dir` for temp directory):

```bash
skillhub --dir /tmp/skillhub-preview/ install <slug>
```

<!--zh
安装完成后，用 `shell_exec` 列出并逐一读取所有文件内容：
-->
After install, use `shell_exec` to list and read all files:

```bash
# 列出所有文件
shell_exec(command="find /tmp/skillhub-preview/<skill-name> -type f | sort")

# 逐一读取（对每个文件执行）

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> 何时使用 → When to Use → 审查协议 → 第一步：来源核查 → Vetting Protocol → Step 1: Source Check
要点    -> Never install a skill without vetting it first. · 不要先正式安装，先安装到临时目录进行审查。 · skillhub 来源 · skillhub source · 平台技能市场 / 我的技能库来源 · Platform market / my skill library source · 所有文件 · 平台官方技能
文件/命令 -> --dir · shellexec · tmp/skillhub-preview · curl/wget · MEMORY.md · USER.md · SOUL.md · IDENTITY.md
内容 SHA-256 -> f37a68a26bdd