Frontend Design Anthropic

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This is a frontend design guidance skill with broad but disclosed UI-focused activation and no hidden code, installer, persistence, credentials, or destructive behavior.

Install this if you want strong opinionated frontend design guidance. Expect it to influence UI aesthetics broadly when a request involves web UI or styling, but the reviewed artifacts do not show sensitive access, automatic execution, persistence, or data exfiltration.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill description is broadly scoped to many kinds of frontend work, including components, pages, artifacts, posters, and applications, which makes it likely to activate for a wide range of loosely related prompts. Over-broad activation can cause inappropriate routing, increasing the chance that this skill overrides more specialized or safer skills and produces unexpected code or design behavior in contexts where it was not intended.

VirusTotal

66/66 vendors flagged this skill as clean.