ClawHub
Back to skill

Security audit

What If Factory

Security checks for vulnerabilities and agentic risk

Overview

This is a creative what-if writing template with no code or special access, though its broad trigger wording could activate in serious hypotheticals.

Install this only if you want playful, meme-style alternate-universe responses. Be aware that ordinary questions containing phrases like "what if" or "suppose" may be treated as creative prompts unless your agent applies stricter intent checks.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
97% confidence
Finding
The top-level description says the skill should trigger when a user says common phrases like 'what if' or 'imagine if', which are widely used in ordinary conversation. This makes accidental invocation likely, causing the agent to apply this skill in unrelated contexts and potentially override more appropriate domain-specific handling.

Vague Triggers

High
Confidence
98% confidence
Finding
The activation guidance explicitly includes broad phrases like 'any phrase containing what if, suppose, imagine if' without meaningful boundaries, which can match a large portion of normal user prompts. In practice this can hijack unrelated conversations, misroute sensitive or serious queries into comedic output, and interfere with safer or more relevant skills.

Static analysis

No suspicious patterns detected.