胡田 OPC导师 苏轼 心智模型

• Outcome: Pass
• Latest audit: May 27, 2026, 4:14 PM
• Version:
  1.0.0

Overview

This is a markdown-only Su Shi perspective skill with broad coaching-style prompts but no evidence of code execution, data access, persistence, or hidden behavior.

Install this only if you want Su Shi-themed reflective guidance. Treat it as philosophical coaching, not medical, legal, crisis, or workplace-harm advice, and be aware that the skill itself says deeper validation is not complete.

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: 89% confidence
• Finding: The skill’s activation examples are broad, everyday life scenarios such as feeling lost at work, balancing life and work, or seeking inspiration. This can cause the skill to trigger in ordinary reflective conversations where a specialized historical-persona framework may be unnecessary, leading to overreach, confusion, or inappropriate persona-shaped advice. The partially completed state of the skill further increases risk because users may receive guidance from an incomplete and insufficiently validated model.

VirusTotal

65/65 vendors flagged this skill as clean.