ClawHub
Back to skill

Security audit

Frontend Design

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only frontend design helper with no hidden execution, credential access, persistence, or destructive behavior.

Install this if you want stronger frontend design guidance. Because it may activate for many frontend tasks, keep using your normal judgment about when it is relevant, and review any generated UI code before deploying, especially if it adds external assets, fonts, scripts, or packages.

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
89% confidence
Finding
The skill description is broadly phrased to activate on nearly any frontend-related request, including websites, pages, dashboards, components, styling, and applications. Overbroad routing can cause inappropriate invocation, increasing the chance that this skill intercepts prompts better handled by safer or more specialized skills, which can expand attack surface and lead to policy bypass through misclassification.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.