Back to skill

Security audit

Usb

Security checks across malware telemetry and agentic risk

Overview

The inspected skill artifacts are coherent workflow helpers with disclosed command use and no evidence of hidden data collection, exfiltration, or unsafe automatic execution.

Install only in a ClawHub/Convex development context where these workflows are expected. Before using the moderation or review-helper paths, confirm the exact command, target, and credentials, and use the documented opt-outs such as --no-yolo when full-access nested review is not appropriate.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.