ClawHub
Back to skill

Security audit

HelloLeads

Security checks across malware telemetry and agentic risk

Overview

The inspected skill artifacts are coherent ClawHub/Convex developer helpers with disclosed powerful commands and no evidence of hidden data theft or persistence.

Install only in a trusted ClawHub development or maintainer context. The skill set includes powerful but disclosed operations, so confirm the active account, command target, and reason before using moderation, PR publishing, UI proof, or full-access review helpers.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.