发现优质的 AI Agent 技能

> Security-first skill vetting for AI agents

Scan OpenClaw skills for security issues before you install them. 341 malicious skills were found on ClawHub — don't be the next victim.

Compare two versions of an OpenClaw skill to find security-relevant changes before updating.

One command to audit your entire skill stack. Chains together arc-skill-scanner, arc-trust-verifier, and generates a comprehensive risk report with prioritized findings.

Assess OpenClaw skills against defined security policies. Track compliance posture across your skill inventory with framework-mapped findings and remediation tracking.

This file contains a conservative baseline derived from OpenClaw’s own security guidance.

This is a convenience map for interpreting `openclaw security audit --json` results.

来自 openclaw/skills 技能

Teach the agent to perform a **defensive, permissioned** security audit of an OpenClaw deployment and produce an actionable report + remediation plan.

OpenExec is a deterministic execution boundary for AI systems. It enforces signed approvals, replay protection, and receipt generation.

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.

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.