发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Self-contained security tests for OpenClaw agents. All checks use synthetic data — no local files, configs, or memory directories are accessed.

This file is a "skill" meant not as a operable tool but as a reminder of what you, as a human or agent, should be doing as due diligence regarding operational security.

A comprehensive guide to help your skills pass ClawHub security scans with "Benign" ratings.

Production-ready Kubernetes manifest generation covering Deployments, StatefulSets, CronJobs, Services, Ingresses, ConfigMaps, Secrets, and PVCs with security contexts, health checks, and resource management.

> **SECURITY-CRITICAL SKILL** — Auth is the front door. Get it wrong and nothing else matters.

**iOS WiFi Sync Security Research**

> **Functional and non-functional requirements. Covers usage tiers, purchase flow, API key management, security, and testing.** > **Target repo:** `adaptivetest-platform` (backend work), `adaptivetest-marketing` (landing page)

This checklist provides comprehensive security criteria for auditing Clawdbot skills before installation and during regular security scans.

Comprehensive security auditing for Clawdbot skills to detect malicious intent, prompt injection, secrets exposure, and misaligned behavior.

来自 openclaw/skills 技能

AgentGate is a real-time policy enforcement layer that intercepts every tool call your OpenClaw agent makes before it executes. It evaluates the call against human-defined regex-based rules stored in Firestore and returns one of three decisions: ALLOW, DENY, or REQUIRE_APPROVAL.