ClawHub
Back to skill

Security audit

Qa Question Framework

Security checks across malware telemetry and agentic risk

Overview

The supplied evidence shows a low-risk prompt-routing concern, not harmful or hidden behavior.

This appears safe to install based on the available evidence. Expect possible over-activation if the skill uses broad clarification-style triggers; uninstall or disable it if it interrupts more specific skills.

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
84% confidence
Finding
The activation conditions are broad enough to trigger on common phrases like not knowing what to ask or needing clarification, which can cause the skill to activate outside its intended scope. This is primarily a prompt-routing and user-experience risk rather than a direct security flaw, but it can override more appropriate skills and lead to unintended behavior.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal