Zhang Xiaolong Perspective V2

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  2.0.0

Overview

This is a persona-style product-thinking skill with broad trigger phrases, but it does not request system access, credentials, persistence, or external actions.

Install this if you want responses shaped by this product-design persona. Before installing, consider narrowing or removing broad triggers such as “克制” and “用户价值” so normal strategy or UX conversations do not unintentionally switch into persona mode.

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 trigger list includes very broad phrases such as “克制” and “用户价值”, which are common in ordinary product, strategy, and UX discussions. This can cause unintended activation of the persona skill during unrelated conversations, leading the agent to override its normal behavior or adopt roleplay unexpectedly when users did not explicitly request it.

VirusTotal

64/64 vendors flagged this skill as clean.