ClawHub
Back to skill

Security audit

Design Extractor Clawhub

Security checks across malware telemetry and agentic risk

Overview

This is a coherent design-documentation skill that scans style files and writes generated design-system outputs, with no artifact-backed evidence of hidden or malicious behavior.

Install only if you want project style files scanned and generated design documentation written into your workspace. Review the referenced npm/GitHub extractor before running npx, and run it in a version-controlled working tree so generated files can be inspected before committing.

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
91% confidence
Finding
The trigger conditions are broad enough to activate on ordinary design-related requests, which can cause the skill to run unexpectedly and scan a project without clear user intent. In this skill's context, automatic activation can lead to unintended repository-wide analysis and follow-on file generation, increasing the chance of surprising or unauthorized workspace modifications.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill describes analysis behavior but does not prominently warn that it writes files into the project workspace, including DESIGN-EXTRACTED.md and JSON output. In agentic environments, undisclosed write behavior is risky because a user may expect read-only analysis, while the skill creates or overwrites artifacts that can affect git state, CI, or downstream automation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.