Why Scan Your OpenClaw Skills?
After the ClawHavoc attack exposed 1,184 malicious skills on ClawHub, scanning OpenClaw SKILL.md files is no longer optional. The AMOS stealer malware targeted browser passwords, cryptocurrency wallets, SSH keys, and API tokens through hidden curl commands embedded in seemingly legitimate skills.
SkillRisk detects malicious hooks, data exfiltration patterns, dangerous permissions, and hidden command execution in your OpenClaw and Claude Code skills — all for free.
OpenClaw Security Scanner Features
- Hook Hijacking Detection — Detects malicious PreToolUse or PostToolUse hooks that execute silent background commands
- ClawHavoc Pattern Matching — Scans for the exact attack patterns used in the ClawHavoc supply chain attack on ClawHub
- Data Exfiltration Prevention — Identifies hidden curl/wget requests that steal credentials and environment variables
- Credential Leak Scanning — Finds hardcoded API keys, SSH keys, and database connection strings
- MCP Server Integrity — Verifies external Model Context Protocol servers for known malicious endpoints
- SKILL.md Analysis — Purpose-built for OpenClaw's SKILL.md format and Claude Code specifications
How It Works
- Upload your OpenClaw SKILL.md file, hook scripts, or .zip folder
- SkillRisk analyzes 646+ security rules across 8 vulnerability categories
- Get an instant security score with detailed risk breakdown and remediation steps
Try the free OpenClaw skill scanner now — no signup required.
Frequently Asked Questions
How does SkillRisk protect against OpenClaw threats like ClawHavoc?
SkillRisk was built with OpenClaw security as a core focus. We scan SKILL.md files, hook scripts, and MCP configurations for the exact attack patterns used in ClawHavoc — embedded curl exfiltration, AMOS stealer payloads, and hidden command execution. With 1,184 malicious skills found on ClawHub and CVE-2026-25253 (CVSS 8.8) still impacting OpenClaw, scanning before installation is essential.
How does SkillRisk differentiate from standard linters?
Unlike general-purpose linters, SkillRisk is specialized for OpenClaw and Claude Code skill specifications. Our rules understand the context of SKILL.md execution, PreToolUse hooks, tool permission hierarchies, and specific MCP server vulnerabilities — including ClawHavoc-style supply chain patterns that general security tools miss.
Are my skill files uploaded to your servers?
If you use the free scan, your files are processed entirely in memory and are never written to disk. We do not store, log, or train on your code.
What file formats does SkillRisk support?
You can upload a .zip of your skill folder. We specifically analyze SKILL.md, settings.json, and any referenced .sh or .js hook scripts used by OpenClaw and Claude Code.