ClawHub
Back to skill

Security audit

Lottery

Security checks across malware telemetry and agentic risk

Overview

The skill package is coherent repo-maintenance guidance with disclosed high-privilege commands, and I found no hidden exfiltration, deception, or unrelated destructive behavior.

Install only for ClawHub/Convex repository maintenance. Review commands before allowing moderation, deploy, migration, PR-comment, or full-access autoreview actions, and use the documented opt-outs or confirmation steps when you want tighter control.

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

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.