Security audit
node-connect
Security checks across malware telemetry and agentic risk
Overview
This is a focused troubleshooting skill for OpenClaw connection and pairing problems, with only expected diagnostic commands and one disclosed device-approval step.
Before installing, expect the skill to guide an agent through OpenClaw and Tailscale connection checks. Treat QR/setup-code JSON, tokens, URLs, and device identifiers as sensitive, and only approve a pending device after confirming it is yours.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.
