← 返回 Skills 市场
14906
总下载
5
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install skill-guard
功能描述
Stage, scan, and install a ClawHub skill when the user requests a guarded ClawHub installation. Blocks installation on security findings or incomplete scans.
安全使用建议
Install only if you are comfortable letting this helper download the requested skill, upload its staged text content to Snyk for analysis, and modify your OpenClaw workspace after a clean scan. Use trusted clawhub and uvx binaries, provide SNYK_TOKEN through a secret manager or environment, and review retained .skill-guard quarantine or backup directories if a scan or replacement fails.
能力评估
Credentials
The required SNYK_TOKEN, clawhub/uvx tools, network access, and workspace file writes are proportionate to guarded installation, but users should understand that staged skill content is sent to Snyk's service for analysis.
Install Mechanism
The shell entrypoint only delegates to the Python helper, which validates slug and version inputs, uses argument-list subprocess calls, downloads through the ClawHub CLI, scans before promotion, and blocks malformed or incomplete results.
Instruction Scope
Runtime instructions are clear about staging, scanning, blocking findings, not executing downloaded skill content, and retaining quarantined files; the manifest does not add a separate machine-readable permission scope.
Persistence & Privilege
The helper creates a private .skill-guard state area, lock file, retained staging directories, and previous-skill backups; this persistence is disclosed and recovery-oriented, not a background service or hidden hook.
Purpose & Capability
The skill has high-impact authority to install or replace a ClawHub skill, but that authority is the stated purpose and is limited to a validated single slug with explicit --force for replacement.
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-guard - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-guard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
v1.0.3
Harden guarded installs: validate inputs, remove scan bypasses, use private staging, require complete scanner results, and retain backups with rollback. Pin Snyk Agent Scan 0.6.3 and fix its parent-directory result handling. Adds regression and real-tool verification scripts. Requires Python 3.9+ and SNYK_TOKEN; authenticated cloud end-to-end verification remains pending.
v1.0.2
Added competitive comparison table. Emphasizes what skill-guard catches that VirusTotal and skillscanner miss: prompt injections, data exfiltration, hidden instructions, AI-specific threats.
v1.0.1
Pre-install security scanning for ClawHub skills
v1.0.0
Initial release: pre-install security scanning for ClawHub skills. Scan before you install — detect prompt injections, malware, secrets, and data exfiltration. Powered by mcp-scan (Invariant/Snyk).
元数据
常见问题
skill-guard 是什么？
Stage, scan, and install a ClawHub skill when the user requests a guarded ClawHub installation. Blocks installation on security findings or incomplete scans. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 14906 次。
如何安装 skill-guard？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-guard」即可一键安装，无需额外配置。
skill-guard 是免费的吗？
是的，skill-guard 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
skill-guard 支持哪些平台？
skill-guard 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-guard？
由 hola（@jamesouttake）开发并维护，当前版本 v1.0.3。
推荐 Skills