ClawHub
Back to skill

Security audit

design-researh

Security checks across malware telemetry and agentic risk

Overview

This appears to be a design or inspiration workflow skill with some broad activation and default external source choices, but no evidence of hidden, destructive, credential-stealing, or persistent behavior.

Install if you want an agent to help with design inspiration and reference gathering. Review or customize the default inspiration sources, especially in a work environment with approved-source policies, and invoke the skill explicitly when you want external research.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill enables implicit invocation while its activation text is broad and covers fuzzy briefs, research, inspiration, and link collection. This can cause the agent to trigger the skill in contexts the user did not clearly intend, leading to unrequested browsing or inclusion of external references, which increases the chance of policy bypass, unwanted data flow, or scope creep.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The default prompt hard-codes Behance, Zcool, Huaban, and Xiaohongshu as default inspiration sources without checking user locale, consent, or platform appropriateness. This can push users toward region-specific external sites by default, potentially causing unexpected external navigation, compliance issues, or mismatches with organizational restrictions and user expectations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.