ClawHub
Back to skill

Security audit

"What if?" Scenario Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only scenario-planning skill with broad activation wording but no hidden execution, data access, persistence, or privilege behavior.

Installers should understand that this skill may activate for a wide range of hypothetical, planning, and brainstorming prompts. That is a routing/usability consideration, not a security concern in this artifact, because the skill is markdown-only and does not request access to files, credentials, tools, or persistent state.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are extremely broad, including generic phrases like 'suppose that', 'thought experiments', 'analyze alternatives', and activation even without explicit 'what if'. In an agent system, this can cause the skill to activate for many ordinary analytical or brainstorming prompts, potentially overriding more appropriate skills and expanding the attack surface for prompt-routing misuse or unintended instruction injection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.