AI Skill Creator (EN)
Security checks across malware telemetry and agentic risk
Overview
The available artifacts are coherent with ClawHub/OpenClaw workflow assistance and show no evidence of hidden malicious behavior.
Install only if you want repo-specific ClawHub/OpenClaw maintenance and Convex workflow guidance. Review commands before running them, especially moderation, publishing, package installation, or broad local review helpers, and make sure the relevant account credentials have the least privilege needed.
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
64/64 vendors flagged this skill as clean.