发现优质的 AI Agent 技能

Real-time security monitoring for OpenClaw agents. Warns when dangerous tool call patterns are detected (reverse shells, credential exfiltration, etc).

**Runtime security scanner and monitor for your OpenClaw agent.**

Runtime Security Hook Pattern for OpenClaw (`agent:before_tool_call`) — warn-first, backward-compatible

Real-time security monitoring for OpenClaw agents. Intercepts dangerous tool calls before execution and checks against threat intelligence patterns.

Static + runtime security scanner for AI agent skills. **135 static patterns + 26 runtime patterns (5 layers)** across **22 categories** — zero dependencies. **0.016ms/scan.**

来自 openclaw/skills 技能

Thanks for your interest in improving agent security! 🛡️

来自 openclaw/skills 技能

Scan, detect, and fix security issues in codebases and infrastructure. Covers dependency vulnerabilities, secret detection, OWASP top 10, SSL/TLS verification, file permissions, and secure coding patterns.

This skill guides the setup of a secure, self-hosted OpenClaw instance. It covers SSH hardening, Firewall configuration, Tailscale VPN setup, and the OpenClaw installation itself.

**Important Security Reminder**: You must complete secure installation steps (see [INSTALL.md](INSTALL.md)) before using this skill. This skill executes external commands and requires careful auditing.

This skill provides a structured, forensically-aware framework for analyzing and securing a Linux host during or after a security event.