ClawHub
Back to skill

Security audit

Jury

Security checks across malware telemetry and agentic risk

Overview

This is a small text-only skill describing a multi-agent deliberation method, with no scripts, install hooks, credential use, or hidden execution behavior found.

This skill appears safe to install as a prompt-only deliberation aid. Treat its legal or ethical verdicts as advisory reasoning rather than professional advice, and verify important conclusions independently.

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.