Security audit
Openclaw Skill
Security checks across malware telemetry and agentic risk
Overview
No concrete harmful behavior was identified, but confidence is limited because the target artifact files were not available for direct review.
Treat this as a clean but lower-confidence result because VirusTotal is still pending and the target files were not available for direct inspection. Before installing, review the skill files in ClawHub for any unexpected credential use, automatic command execution, broad file access, or persistent background behavior.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.