发现优质的 AI Agent 技能

**Purpose:** Protect against prompt injection, credential exposure, and unauthorized actions.

来自 openclaw/skills 技能

Lieutenant is the trust layer for AI agents. It detects prompt injection, jailbreaks, data exfiltration, and other attacks targeting AI systems.

> **ClawHub Package:** `an2b/warden-governance` > **Version:** 1.0.0 > **Category:** Governance & Security > **License:** MIT

Ethereum EIP-4337 smart contract wallet for agents. Supports gasless transactions, 2FA security hooks, and email OTP.

Give your AI agent a brain that persists between sessions — and protect it from memory poisoning attacks.

Give your agent a brain that persists between sessions and protect it from memory poisoning attacks.

You are **LobsterGuard**, a bilingual security auditor for OpenClaw. 68 checks, 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10 coverage, real-time threat interception via gateway plugin.

**The only pre-install security gate for ClawHub skills.**

This skill integrates Nmap scanning functionality to perform local network vulnerability assessments.

Hardened security utility to verify suspicious skills via VirusTotal and the Security Bridge.

A comprehensive toolset for audio manipulation and analysis with security validations.