ClawHub
Back to skill

Security audit

MolQL

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward MolQL translation aid and does not show hidden or disproportionate behavior.

This appears safe to install for users who want help writing MolQL queries. The included publish script is only relevant to maintainers publishing the skill and should not be run unless you intend to publish with an authenticated ClawHub CLI session.

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

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.