← 返回 Skills 市场
Skill Vetter
作者
spclaudehome
· GitHub ↗
· v1.0.0
259410
总下载
1225
收藏
4728
当前安装
1
版本数
在 OpenClaw 中安装
/install skill-vetter
功能描述
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.
安全使用建议
Safe to install as a manual vetting checklist. When using it, only fetch repositories you intend to review, verify placeholders before running the curl examples, and treat any downloaded skill text as untrusted content.
功能分析
Type: OpenClaw Skill
Name: skill-vetter
Version: 1.0.0
This skill, 'skill-vetter', is designed to help AI agents identify security risks in other skills. The `SKILL.md` file outlines a vetting protocol, including a comprehensive list of 'RED FLAGS' for agents to look for in untrusted code. The 'Quick Vet Commands' section uses `curl` to fetch metadata and file contents from GitHub (api.github.com, raw.githubusercontent.com) for *other* skills, which is directly aligned with its stated purpose of vetting. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection against the agent itself; rather, it instructs the agent on how to detect such behaviors in external skills.
能力评估
Purpose & Capability
The artifact is a single SKILL.md whose instructions match the stated purpose of security vetting other skills; it contains no runnable code, data exfiltration path, credential request, or destructive behavior.
Instruction Scope
It asks agents to read third-party skill files and optionally fetch GitHub content, which is necessary for vetting but means reviewed files must be treated as untrusted evidence rather than instructions to follow.
Install Mechanism
No install scripts, dependencies, or executable files are present; metadata shows limited external provenance, but the artifact itself is low-impact.
Credentials
The only environment interaction described is optional curl/jq commands to GitHub APIs and raw GitHub content for user-selected repositories, which is proportionate to skill review.
Persistence & Privilege
The skill requests no persistence, background worker, elevated privilege, credential store access, local profile/session access, or system modification.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install skill-vetter - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-vetter触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release - Security-first skill vetting for AI agents
元数据
常见问题
Skill Vetter 是什么？
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 259410 次。
如何安装 Skill Vetter？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-vetter」即可一键安装，无需额外配置。
Skill Vetter 是免费的吗？
是的，Skill Vetter 完全免费（开源免费），可自由下载、安装和使用。
Skill Vetter 支持哪些平台？
Skill Vetter 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Skill Vetter？
由 spclaudehome（@spclaudehome）开发并维护，当前版本 v1.0.0。
推荐 Skills