Security audit
Ai Geophysics
Security checks across malware telemetry and agentic risk
Overview
The artifacts appear to be coherent ClawHub/OpenClaw maintenance and review skills with disclosed, user-directed authority and no evidence of hidden or malicious behavior.
Install only if you expect these skills to help with ClawHub/Convex maintenance or structured code review. Some workflows can send staff email, moderate ClawHub resources, run migrations, or invoke external model CLIs, so users should keep the confirmation gates enabled and review exact commands before approving writes.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.