Korean

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only Korean writing style helper; its main risk is tone appropriateness, not security behavior.

Install is reasonable from a security perspective. Tell the agent when you need polite, formal, professional, family-safe, or non-slang Korean, because the skill otherwise pushes casual online wording and includes some crude slang examples.

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: 91% confidence
Finding: The skill explicitly sets casual/informal Korean as the default and normalizes 반말 unless the user asks for formality. This can cause outputs that violate user expectations, social norms, or professional context, especially when the user did not opt into informal speech. In assistant settings, forcing a lower register can lead to disrespectful, inappropriate, or reputationally harmful responses.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal