Back to skill

Security audit

china-video-prompt-architect

Security checks across malware telemetry and agentic risk

Overview

This skill is a scoped video-prompt writing assistant with a clearly disclosed optional helper install, and no artifact-backed evidence of hidden data access or unsafe behavior.

Safe to use for drafting video-generation prompts. Review the optional MCP install separately before enabling it, because npx will run code from the referenced GitHub package even though the skill describes those helpers as read-only and optional.

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

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.