ClawHub
Back to skill

Security audit

Six Thinking Hats

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only facilitation skill for structured decision discussions, with no executable code or hidden system access.

Installers should know this skill may activate on broad meeting-language cues, so it is best used when the user actually wants a structured multi-angle decision discussion. It does not appear to run code, access private data, install persistence, or change the system.

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation criteria include broad conversational phrases like 'we need structure' and 'let's look at this from all angles,' which can appear in ordinary discussion and cause unintended skill activation. In an autonomous or semi-autonomous agent system, this can divert the agent into a structured facilitation workflow when the user did not explicitly request it, creating prompt-routing errors and possible interference with higher-priority instructions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The 'When to Use' section repeats ambiguous examples such as 'let's look at this from all angles' and 'we keep going in circles' without defining clear invocation thresholds. This increases the chance of accidental activation across normal workplace conversations, which can lead to misclassification of user intent and unnecessary control of the interaction flow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.