前端设计

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Chinese frontend design skill with no code execution or special access; its main risks are broad activation and language preference handling.

Install this if you want a Chinese-language frontend design assistant that pushes for distinctive visual direction. Review generated HTML/CSS/JavaScript before production use, and override or avoid the skill when you need a simpler coding answer, a different response language, or a narrower frontend workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger conditions are very broad and match common requests like 'help me write a webpage' or any mention of React/Vue/HTML/CSS. In an agent environment, this can cause the skill to activate for routine frontend questions where a narrower or more general coding skill would be more appropriate, leading to over-application of strong stylistic instructions and reduced user-intent fidelity.

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The skill metadata and description are written as Chinese-language behavioral guidance without indicating that response language should follow the user's preference. If the runtime treats this as instruction, the skill may steer outputs into Chinese even when the user asked in another language, causing instruction conflict, degraded usability, and possible mishandling in multilingual workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal