发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Security scanner for agent skills. 48 critical checks, 8 warning checks. No dependencies — just bash and grep. Includes Tirith-inspired detection patterns, campaign signatures from [Koi Security](https://www.koi.ai/blog/clawhavoc-341-malicious-clawedbot-skills-found-by-the-bot-they-were-targeting), [Bitdefender](https://businessinsights.bitdefender.com/technical-advisory-openclaw-exploitation-enterprise-networks), [Snyk](https://snyk.io/articles/clawdhub-malicious-campaign-ai-agent-skills/), and

*Don't just scan for threats. Learn to think about them.*

> **用途**：对 OpenClaw 部署进行安全配置审计，检测已知漏洞和安全隐患 > **版本**：1.0.0 > **作者**：Security Team > **风险等级**：安全审计工具（仅读取和检测，不修改任何配置）

Security toolkit for AI agents. Scans skills for malware, sanitizes external input, and blocks prompt injection attacks.

> **Security note:** The examples below generate a private key and print it to stdout so you can capture the address. The private key should be stored in an external signer, OS keychain, or encrypted vault — **not** persisted to plaintext files by default. See the "Persisting Credentials" section below and "Private key handling" in SKILL.md for the full decision flow.

Structured security audit for Node.js HTTP servers and web applications.

All webhook requests sent by Moralis Streams are signed with your streams secret to verify authenticity.

This document outlines the permissions and security considerations for the `model-manager` skill.

Security skill that scans code, config files, and repos for accidentally leaked secrets and credentials.

Security skill that scans code, config files, and repos for accidentally leaked secrets and credentials.

**Enhanced Malicious Skill Detection Tool** - With anti-obfuscation and anti-evasion detection capabilities