← 返回 Skills 市场
4707
总下载
12
收藏
30
当前安装
1
版本数
在 OpenClaw 中安装
/install clawdbot-security-suite
功能描述
Advanced security validation for Clawdbot - pattern detection, command sanitization, and threat monitoring
安全使用建议
Install only if you specifically want a local Clawdbot security validation layer. Prefer manual validation first; enable the automatic hook only after reviewing its shell invocation and fail-open behavior. Treat logs as sensitive, because commands, URLs, paths, and tool arguments may be retained locally. Do not treat an ALLOWED result as permission to run destructive or privileged commands without normal user approval.
功能分析
Type: OpenClaw Skill
Name:
Developer:
Version:
Description: OpenClaw Agent Skill
The bundle is a legitimate security suite designed to provide runtime protection for OpenClaw agents against command injection, SSRF, path traversal, and prompt injection. It implements a pattern-matching engine in bash (security.sh) and a TypeScript hook (handler.ts) that intercepts tool calls to validate arguments against a comprehensive set of security regexes in patterns.json. The logic is transparent, operates locally without external data exfiltration, and the instructions provided to the AI agent (SKILL.md, CLAWDBOT-INSTRUCTIONS.md) are strictly aligned with enforcing security boundaries and best practices.
能力评估
Purpose & Capability
The stated purpose of validating commands, URLs, paths, and content matches the Bash validator, pattern file, and hook behavior; prompt-injection phrases appear as detection examples, not hidden evaluator instructions.
Instruction Scope
The optional hook is documented to run automatically on every tool call, and the handler validates broad tool categories while allowing execution when validation is missing, unclear, or errors.
Install Mechanism
Installation into ~/.clawdbot/skills and optional hook installation into ~/.clawdbot/hooks are disclosed, but manual download examples use remote code without pinned checksums or signatures.
Credentials
The hook and CLI write persistent local logs under ~/.clawdbot/logs/security-events.log, including raw commands, URLs, paths, and full pre-call argument objects without visible redaction.
Persistence & Privilege
Enabling the hook persistently changes agent tool-call behavior and invokes the local validator through execSync with a constructed shell command containing user-controlled arguments.
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 clawdbot-security-suite - 安装完成后，直接呼叫该 Skill 的名称或使用
/clawdbot-security-suite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: Comprehensive AI agent security
Features:
• 50+ threat detection patterns from security research
• Command injection, SSRF, path traversal protection
• Prompt injection and API key exposure detection
• Real-time security monitoring and event logging
• Manual integration + automatic hooks
• Complete documentation and examples
Built for Clawdbot with plans to expand to other AI agents.
元数据
常见问题
Clawdbot Security Suite 是什么？
Advanced security validation for Clawdbot - pattern detection, command sanitization, and threat monitoring. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4707 次。
如何安装 Clawdbot Security Suite？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install clawdbot-security-suite」即可一键安装，无需额外配置。
Clawdbot Security Suite 是免费的吗？
是的，Clawdbot Security Suite 完全免费（开源免费），可自由下载、安装和使用。
Clawdbot Security Suite 支持哪些平台？
Clawdbot Security Suite 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 Clawdbot Security Suite？
由 gtrusler（@gtrusler）开发并维护，当前版本 v1.0.0。
推荐 Skills