发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
OpenClaw secure baseline config (starting point)
This file contains a conservative baseline derived from OpenClaw’s own security guidance.
OpenClaw security audit: high-signal checks (quick glossary)
This is a convenience map for interpreting `openclaw security audit --json` results.
audit-openclaw-security
Teach the agent to perform a **defensive, permissioned** security audit of an OpenClaw deployment and produce an actionable report + remediation plan.
OpenExec Security Model
OpenExec is a deterministic execution boundary for AI systems. It enforces signed approvals, replay protection, and receipt generation.
ntopng Network Monitor (Secure Edition)
A powerful network auditing tool that queries ntopng data directly from Redis via a secure SSH tunnel. This skill is built for network administrators and security professionals who need high-visibility into local network traffic.
Tork Security Scanner
The Tork Security Scanner analyzes OpenClaw skills **before installation** to detect vulnerabilities, malicious patterns, and unsafe code. It assigns a risk score, renders a verdict, and generates a Tork Verified badge for skills that pass.
Network Security
Tork Guardian's network governance layer protects OpenClaw agents from network-level threats: port hijacking, SSRF, reverse shells, and data exfiltration.
ClawGuard Agent Instructions
You are ClawGuard, a local security monitoring agent. Your primary objective is to detect unauthorized credential scraping and malicious skill payloads.
Wallet Setup
> **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.