胡田-OPC导师-沙盘推演

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 5:08 PM UTC
• Version:
  1.0.0

Overview

This appears to be a decision-support skill with an overly broad trigger, but no evidence of hidden access, data theft, persistence, or destructive behavior.

Installers should be aware that this skill may engage in more general decision-making conversations than expected. If installed, consider narrowing its trigger to explicit scenario-simulation or decision-review requests.

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 (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger conditions are overly broad and describe common business situations such as needing to evaluate options or make a major decision. This can cause the skill to activate in many ordinary conversations without clear user intent, increasing the chance of unwanted routing, context capture, or the model applying a specialized decision framework when it was not explicitly requested.

VirusTotal

59/59 vendors flagged this skill as clean.