Soft Skill

Security checks across malware telemetry and agentic risk

Overview

This is a design-style guidance skill with strict aesthetic preferences, not a skill that runs code, accesses data, or changes system settings.

Install this if you want the agent to strongly favor a specific high-end visual-design style. Be prepared to explicitly override it when you need different branding, accessibility choices, simpler UI, existing design-system compliance, or standard project icons and fonts.

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: 86% confidence
Finding: The skill strongly constrains outputs to a single premium visual style and explicitly prohibits common alternatives, which can override user preferences or task requirements if invoked without clear consent. In this context the content is design-focused rather than code-execution or data-exfiltration oriented, so the main risk is unwanted steering, reduced user agency, and possible conflict with accessibility, branding, or project constraints.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal