Trusted Skills for AI Agents
Every skill in our directory is automatically scanned for malicious content. Verified skills go further — they've passed manual code review by our team.
Why This Matters
We discovered 210+ malicious skills disguised as legitimate tools in the OpenClaw ecosystem. These skills embedded hidden payloads that attempted to execute remote code on users' machines. We removed them all and built automated defenses to prevent this from happening again.
Read the full storyOur Security Process
1. Automated Scan
Every skill is scanned for base64 payloads, known malicious IPs, suspicious install commands, and other attack patterns. Skills scoring above our threshold are automatically blocked.
2. Manual Review
Flagged skills are manually reviewed by our team. We check the source code, installation process, and runtime behavior before making a decision.
3. Verification
Skills that pass full code review earn the Verified badge. This means the code has been audited for security, functionality, and quality by our team.
Verified Skills
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web.
npx clawhub@latest install artifacts-builderbrowse
Complete guide for creating and deploying browser automation functions using the stagehand CLI
npx clawhub@latest install browsecoding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent.
npx clawhub@latest install coding-agentdocker-essentials
Essential Docker commands and workflows for container management, image operations.
npx clawhub@latest install docker-essentialsmcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external servi.
npx clawhub@latest install mcp-builderFor Skill Creators
Getting your skill verified is free and signals to users that your skill is safe and well-maintained.
- Verified badge on your skill card
- Featured placement in the directory
- Increased trust and adoption
- Priority support from our team
For Users
Look for these badges when browsing skills to understand their security status: