ClawHub
Back to skill

Security audit

What If Factory

Security checks across malware telemetry and agentic risk

Overview

This is a creative what-if writing skill with overly broad trigger wording, but it does not show hidden access, persistence, data collection, or destructive behavior.

Safe to install for entertainment and creative brainstorming. Be aware it may activate too easily on ordinary hypothetical questions; use explicit wording when you want the full parallel-universe format, and ask your agent to skip the skill for factual planning or normal reasoning.

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

High
Confidence
95% confidence
Finding
The skill description is broad enough to activate on many ordinary phrases like 'what if' or 'imagine if', which are common in normal conversation and not limited to explicit user intent to use this skill. This creates prompt-routing risk: the agent may invoke the skill unexpectedly, override a more suitable tool or response mode, and force a rigid output structure the user did not request.

Vague Triggers

High
Confidence
97% confidence
Finding
The catch-all trigger 'Any phrase containing' broad speculative terms and 'wild idea' has unclear boundaries and can capture a large amount of benign conversation. In practice this increases accidental activation, causing the agent to follow strict formatting instructions even when the user only wants a simple answer, which is a form of behavior hijacking at the routing layer.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.