Moon Lovers Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed romantic roleplay reply-writing aid with no evidence of malware, data theft, persistence, or hidden execution.

Install only if you want a Chinese-first romantic roleplay/reply-writing style skill. Review the extra reference profiles if youth-coded fictional character styles or default persona self-references are not appropriate for your use case, and keep any skill/MCP installation recommendations under explicit user control.

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)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The profile hard-codes a Chinese self-reference style (e.g., using '环儿') and dialogue conventions without checking the user's language preference or obtaining opt-in. In a chat skill, this can cause unwanted language switching, reduce usability, and override user expectations, especially for multilingual or non-Chinese users.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal