Japanese
Security checks across malware telemetry and agentic risk
Overview
This is a text-only Japanese writing-style skill with no code execution, data access, persistence, or hidden behavior.
Safe to install from a security perspective. Users should still review generated Japanese for context, because the skill intentionally favors casual, slang-heavy, and sometimes blunt wording that may be inappropriate in formal or professional settings.
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.