Zaregoto Miko Style

Security checks across malware telemetry and agentic risk

Overview

This text-only skill rewrites user-provided text in a Chinese character-inspired style and does not request access to files, accounts, commands, or background processes.

Install this if you want a niche Chinese style-conversion helper. Be aware it may trigger on broad style-conversion requests and may answer in Chinese unless the user or agent constrains language, but the reviewed artifacts do not show security-sensitive behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill metadata and body strongly prescribe Chinese output and a specific Chinese style transformation without indicating any language preference detection or user opt-in. This can cause unintended language switching, reduced usability, and prompt-routing surprises, especially when the user input or broader session is in another language.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal