Game Theory Debate

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is an instruction-only decision-analysis skill with disclosed broad triggers and no executable code or credential access.

Install this if you want decision questions automatically framed as game-theory analysis. Review the broad trigger behavior first, and be cautious about pairing it with memory or self-improvement skills if your decisions may include sensitive personal, business, or financial details.

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 (2)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger conditions are very broad and match common conversational phrases like asking for advice, comparing options, or expressing hesitation. This can cause the skill to activate unexpectedly in ordinary chats, overriding user intent and injecting unsolicited decision-making behavior into unrelated contexts.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The description is written only in Chinese and does not indicate whether the skill supports other languages or follows the user's language preference. In a multilingual agent environment, this can cause confusing behavior, reduce transparency, and make users unable to understand when or why the skill activates.

VirusTotal

64/64 vendors flagged this skill as clean.