Six Thinking Hats

Security checks across malware telemetry and agentic risk

Overview

This is a coherent decision-analysis skill that stores limited local preferences and optional analysis history, with no code execution, network access, or credential use found.

Safe to install for structured decision help. Be aware it may create ~/six-thinking-hats/ and retain decision preferences or recent analyses locally; review or delete that folder, or decline archiving, if you do not want that history kept.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The instruction to 'save immediately' encourages persistent collection of user preferences without requiring clear notice, consent, or data-minimization controls. In a decision-support skill, these preferences may reveal sensitive behavioral, professional, or personal information over time, creating privacy risk if stored unexpectedly or retained too broadly.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal