ClawHub

Material Design Skill

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Material Design 3 reference skill with no executable code, credential access, persistence, or hidden data handling.

Safe to install as a low-risk reference skill. Review copied code examples before production use, and consider narrowing automatic activation if generic UI or design prompts trigger it too often.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list includes broad phrases such as “设计系统” and “Android UI”, which can overlap with ordinary design or development conversations and cause unintended activation. This is not a code-execution issue, but it can route users into the wrong skill context, creating misleading responses or unwanted behavior selection.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes very broad and generic terms such as "Compose", "Typography", "按钮样式", and general UI/design phrases, which can cause the skill to activate for unrelated requests. Over-broad activation can route users into the wrong skill context, increasing the chance of misleading answers, prompt-surface expansion, and interference with more appropriate or safer skills.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal