Back to skill

Security audit

Cover Letter

Security checks across malware telemetry and agentic risk

Overview

The reviewed skill artifacts appear coherent and clean, with sensitive actions described as explicit, user-directed workflows rather than hidden behavior.

Install this only if you expect the described ClawHub or operational workflows and have authority to use the relevant credentials. Before any write, email, deploy, deletion, moderation, or transfer action, confirm the exact target, reason, and command.

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.