ClawHub
Back to skill

Security audit

Draft

Security checks across malware telemetry and agentic risk

Overview

This is a drafting-only skill with broad activation wording but no code execution, data access, persistence, or hidden behavior.

Installers should expect this skill to activate broadly for draft-writing requests. Review generated text before sending or publishing, especially for sensitive, legal, financial, business, or public communications.

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

High
Confidence
95% confidence
Finding
The trigger description is extremely broad, covering nearly any request to write or turn notes into a document. This can cause the skill to activate outside its intended scope, potentially intercepting unrelated user tasks and influencing outputs when another, more appropriate skill should handle the request.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal