ClawHub

Ai Skateboarding

Security checks across malware telemetry and agentic risk

Overview

This is a simple skateboarding reference skill with no code or system access, though users should treat its trick guidance as educational rather than a substitute for safe in-person instruction.

This appears safe to install from an agent-security perspective because it is documentation-only and does not access your system. Before using its skateboarding advice, especially for advanced moves like drop-ins, grinds, slides, downhill, or airs, use proper protective gear, progress gradually, and seek in-person coaching or supervision when 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
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill provides instruction for inherently risky physical activities such as drop-ins, grinds, slides, downhill skating, and airs, but lacks a prominent upfront safety disclaimer and clear boundaries for beginners. In this context, omission of explicit risk warnings can contribute to unsafe real-world behavior, especially if novice users treat the guidance as sufficient without protective gear, supervision, or gradual progression.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal