ClawHub
Back to skill

Security audit

Virtual Try-On

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed prompt-only virtual try-on workflow with clear consent and AI-labeling guardrails, and it does not add hidden code execution or persistence.

Install only if you are comfortable using your configured image generator with the supplied photos. Use photos you own or have permission to use, avoid third-party likenesses without consent, and label outputs as AI-generated.

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.