ClawHub
Back to skill

Security audit

Structure Thinking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only problem-structuring guide with no executable code, persistence, credential use, or hidden authority.

Before installing, expect this skill to shape how the agent frames complex problems and recommendations. It should not need special permissions or access to private data beyond whatever information you choose to provide in the conversation.

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

Low
Confidence
82% confidence
Finding
The manifest's default prompt uses the trigger-like phrase "$structure-thinking" but does not define when the skill should or should not be invoked, nor does it provide any exclusion conditions or scope boundaries. While the phrase is somewhat domain-specific, the file still lacks specificity about trigger constraints, which can lead to unintended activation in loosely matched contexts.

Static analysis

No suspicious patterns detected.