← 返回 Skills 市场
469
总下载
0
收藏
8
当前安装
3
版本数
在 OpenClaw 中安装
/install skill-shell
功能描述
Evaluate external skills before installation and decide whether to install, reject, or absorb only the useful ideas. Use when a user shares a ClawHub/GitHub...
安全使用建议
This skill is a low-risk, coherent checklist for reviewing other skills. Before using it: (1) do dynamic validation only after explicit user approval and inside an isolated environment (sandbox/container) if the review requires running code or fetching external artifacts; (2) never grant the agent credentials or broad filesystem access to perform a review — instead provide a copy of the package or a controlled environment; (3) watch for dynamic validation steps that run installers, curl/wget to unknown endpoints, or request tokens — those require manual oversight; and (4) treat the skill as guidance (absorb ideas) rather than an automatic executor of installation steps unless you trust the source.
功能分析
Type: OpenClaw Skill
Name: skill-shell
Version: 0.2.2
The skill-shell bundle is a security-focused meta-skill designed to help the OpenClaw agent evaluate and audit other third-party skills before installation. It contains no executable code and consists entirely of instructional Markdown (SKILL.md and references/checklist.md) that establishes a robust security framework, explicitly instructing the agent to look for and reject red flags such as credential theft, data exfiltration, and unauthorized network calls.
能力评估
Purpose & Capability
Name, description, and SKILL.md all describe the same responsibility: reviewing/triaging candidate skills. No unexpected binaries, env vars, or installs are requested — everything is proportionate to a review/meta skill.
Instruction Scope
The instructions are intentionally broad (static review + dynamic validation). They recommend inspecting package contents and, when required, performing dynamic checks which could involve network fetches or running installers. That scope is appropriate for a vetting workflow, but it means dynamic validation steps should only be performed with explicit user approval and in an isolated environment.
Install Mechanism
No install spec and no code files — the skill is instruction-only, which minimizes disk writes and execution risk.
Credentials
No credentials, env vars, or config paths are requested. The SKILL.md warns about reading sensitive locations (e.g. ~/.ssh, ~/.aws) as red flags rather than instructing the agent to read them, which is appropriate.
Persistence & Privilege
The skill is not force-included (always:false) and does not request persistent privileges or to modify other skills or system settings.
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-shell - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-shell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
v0.2.2
Test publish using the new clawhub-publish-flow local script. No behavior change beyond validating the release workflow.
v0.2.1
Absorb security vetting heuristics from skill-vetter: explicit red-flag list, clearer source/version reporting, red-flags output section, and risk-level labels. Built by 石屹 for 加十.
v0.2.0
Initial public release of the refined skill review model. Built by 石屹 for 加十.
元数据
常见问题
Skill Shell 是什么？
Evaluate external skills before installation and decide whether to install, reject, or absorb only the useful ideas. Use when a user shares a ClawHub/GitHub... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 469 次。
如何安装 Skill Shell？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-shell」即可一键安装，无需额外配置。
Skill Shell 是免费的吗？
是的，Skill Shell 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Skill Shell 支持哪些平台？
Skill Shell 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 Shell？
由 G-Hanasq（@g-hanasq）开发并维护，当前版本 v0.2.2。
推荐 Skills