Strategic Thinking & Mental Models Engine

• Outcome: Pass
• Latest audit: May 28, 2026 at 8:30 AM UTC
• Version:
  1.0.0

Overview

This is a markdown-only decision-support skill that gives structured thinking frameworks and does not ask for private data, system access, or background execution.

Reasonable to install as a structured decision aid. Be aware that its broad trigger phrases may make it appear during ordinary decision conversations, and treat business, investing, or personal recommendations as frameworks to review rather than professional advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrase 'Help me decide [your decision]' is broad and closely matches normal user speech, so the skill may activate in many unrelated conversations involving ordinary decision-making. Because this skill is a general-purpose decision framework, accidental invocation could override or interfere with other skills or agent behavior more often than a narrowly scoped trigger would.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The invocation guidance does not clearly define scope boundaries, so the assistant may activate the skill for many loosely related requests involving decisions. This ambiguity increases the chance of accidental routing and response interference, especially because decision language appears in many benign conversations across domains.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The invocation guidance does not clearly define scope boundaries, so the assistant may activate the skill for many loosely related requests involving decisions. This ambiguity increases the chance of accidental routing and response interference, especially because decision language appears in many benign conversations across domains.

VirusTotal

66/66 vendors flagged this skill as clean.