发现优质的 AI Agent 技能

> **🔒 Security Note:** This skill mentions API keys, tokens, and webhook URLs because it teaches you how to set up integrations with Linear, Discord, and automation services (Make.com, Pipedream, Zapier). These are necessary for the tutorial — the skill does NOT collect or transmit your credentials. All setup happens on your local machine and the services you configure.

> **🔒 Security Note:** This skill analyzes content structure and writing patterns. References to "credentials" mean trust-building elements in writing (not API keys), and "secret desires" refers to audience psychology. No external services or credentials required.

**Copy this section to your AGENTS.md file.**

Scan OpenClaw skills for malware, suspicious patterns, and install traps BEFORE installing them.

This document covers security best practices when deploying and using the `sql-server-skills` scripts in production SQL Server environments.

来自 openclaw/skills 技能

This skill is shell-based and modifies local OpenClaw config. It is designed to be bounded, explicit, and reversible.

Scan your installed OpenClaw skills for security threats that traditional antivirus cannot detect — prompt injection, data exfiltration, persistence manipulation, privilege escalation, supply chain attacks, and semantic worms.

The flagship adversarial security testing skill for the VEXT Shield suite. Simulates a hostile attacker probing an OpenClaw skill for exploitable weaknesses — prompt injection susceptibility, data boundary violations, unauthorized persistence, data exfiltration, privilege escalation, and self-replicating worm behavior.

Aggregated security dashboard for your OpenClaw installation. Combines scan results, monitor alerts, audit reports, red team findings, and firewall violations into a single security posture report.

Run a full security audit of your OpenClaw installation. Checks configuration best practices, file permissions, network exposure, identity file integrity, and scans all installed skills.

AI-native security for the agentic era. Detects threats that VirusTotal and traditional scanners cannot: prompt injection, semantic worms, cognitive rootkits, data exfiltration, permission boundary violations, and behavioral attacks.