ClawHub
Back to skill

Security audit

Edic Design System

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a prompt-style design helper with no evidence of malware, hidden execution, data theft, or destructive behavior.

Before installing, check that the skill's README clearly states when to use it and when not to use it. Treat it as design guidance, not an authority to make broad repository changes unless you explicitly ask for EDIC-specific transformations.

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
86% confidence
Finding
The README instructs users to invoke the skill with a broad natural-language phrase and does not define clear trigger boundaries, exclusions, or scope limits. In agent environments, overly broad activation guidance can cause the skill to be applied unintentionally to unrelated styling or refactoring requests, increasing the chance of prompt/skill overreach and unsafe persistence of its instructions across tasks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.