ClawHub
Back to skill

Security audit

Jobs To Be Done Analyzer

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only product-analysis skill with no code execution, credential access, or persistence.

Safe to install as a brainstorming and customer-research aid. Be aware it may activate for broad product questions, and treat any confidential customer or business research you paste into your assistant as sensitive.

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
95% confidence
Finding
The trigger list is overly broad and includes common phrases like "what problem," "user needs," and "why do people buy," which can cause the skill to activate in many general product, research, or strategy conversations where JTBD analysis was not specifically requested. This creates routing ambiguity and can lead to inappropriate invocation, crowding out more suitable skills or causing the agent to follow a mismatched analysis workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.