Design To Code

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only design-to-code helper, and its behavior matches its stated purpose without hidden access or execution.

Safe to install for frontend design implementation help. Be aware it may activate on broad UI phrases, so confirm that a request really involves a design mockup or design-to-code task, and review generated code changes before applying them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation guidance is broad enough to trigger on common user phrases such as '按设计稿实现' or '设计转代码', and also on the presence of links or screenshots. This can cause the skill to activate outside narrowly intended contexts, increasing the chance of unintended behavior, incorrect routing, or handling of inputs that were not meant for this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal