hook-guard钩子守卫。为 Agent 操作添加安全防护层——文件修改前自动备份、危险命令执行前拦截确认、敏感操作自动告警通知用户。触发词：安全检查、hook guard、守卫、备份保护、安全模式、操作审计。也可在 AGENTS.md 中配置为始终生效。
Install via ClawdBot CLI:
clawdbot install wavmson/hook-guardGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://github.com/wavmson/openclaw-skill-hook-guard.gitAI Analysis
The skill's core function is to add safety checks and backups to agent operations, which is a protective measure. The external URL reference appears to be a standard git repository link for the skill's source code, not an active data exfiltration endpoint. The main risk is the potential for the skill's 'dangerous command' detection logic to be bypassed or misconfigured.
Audited Apr 18, 2026 · audit v1.0
Generated May 7, 2026
在部署关键服务或应用时，Hook Guard 自动拦截危险操作（如 rm -rf、sudo 命令），并提示用户确认或提供替代方案（如 trash）。这避免了误操作导致的生产事故，尤其适合运维团队管理远程服务器。
当 AI 代理修改 nginx.conf、openclaw.json 等配置文件时，Yellow Hook 自动备份原文件到安全目录，并通知用户。用户可随时回滚，防止配置错误引发服务中断。
Green Hook 记录所有常规操作日志，Red Hook 拦截高风险操作并要求确认，形成完整审计链。适用于金融、医疗等合规要求严格的行业，满足数据操作可追溯性。
在 Swarm Coord 场景中，子 Agent 的操作也受 Hook Guard 保护。例如，一个 Agent 请求删除文件，Hook Guard 会仲裁并拦截，防止单个 Agent 误判导致整体系统受损。
Hook Guard 自动备份修改的文件并保留 7 天，用户可随时查看备份清单。定期演练时，通过回滚旧备份快速恢复到某时间点，降低数据丢失风险。
将 Hook Guard 作为云服务提供，按月或按年订阅。企业集成后，无需自建安全钩子系统，降低开发成本。
为大型企业提供定制化 Hook Guard 部署，包括与现有系统集成、审计日志可视化仪表盘、合规报告自动生成。
基础版本免费提供 Green 和 Yellow 钩子，Red 钩子（危险操作拦截）为付费功能。吸引开发者试用，再引导升级。
💬 Integration Tip
在 AGENTS.md 中添加安全规则即可全局生效；建议先测试 Yellow 和 Green 钩子，再启用 Red 钩子避免日常干扰。
Scored May 7, 2026
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L...
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included.
Audit codebases and infrastructure for security issues. Use when scanning dependencies for vulnerabilities, detecting hardcoded secrets, checking OWASP top 10 issues, verifying SSL/TLS, auditing file permissions, or reviewing code for injection and auth flaws.
Audit a user's current AI tool stack. Score each tool by ROI, identify redundancies, gaps, and upgrade opportunities. Produces a structured report with score...
Detect anomalies and outliers in construction data: unusual costs, schedule variances, productivity spikes. Statistical and ML-based detection methods.