ClawHub
Back to skill

Security audit

Counterfactual Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only reasoning skill for counterfactual analysis, with somewhat broad activation wording but no code, data access, persistence, or hidden behavior.

Install this if you want the agent to use structured counterfactual reasoning. Be aware it may steer broad decision reviews or mistake analysis into this framework even when a narrower approach would be enough.

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

Medium
Confidence
91% confidence
Finding
The description triggers on very broad situations like analyzing past decisions, understanding causation, learning from mistakes, or evaluating alternatives, which are common across many normal user requests. Overly broad activation criteria can cause the skill to be invoked unnecessarily, increasing prompt-surface area and the chance that its instructions interfere with more appropriate, narrower skills or context-specific safety handling.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The instruction to apply the framework to whatever the user is currently working on is highly expansive and effectively removes meaningful scope boundaries. This makes accidental or excessive activation more likely, allowing the skill to steer unrelated conversations into its framework and potentially override more suitable tools, constraints, or safety-specialized handling.

Static analysis

No suspicious patterns detected.