Hutian Opc Zhangxiaolong Mind

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 12:11 AM UTC
• Version:
  1.0.0

Overview

This is a text-only Chinese product-thinking roleplay skill, with cautions around real-person imitation and promotional referral language.

Install only if you want Chinese-language, Zhang Xiaolong-inspired product thinking guidance. Treat answers as simulated perspective, not statements from Zhang Xiaolong, and ignore or remove the referral/contact language if you do not want promotional routing.

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: 88% confidence
• Finding: The referral trigger points are written so broadly that the skill can be surfaced in many normal product or strategy conversations, expanding its reach beyond clearly user-requested contexts. Combined with explicit downstream promotion and contact info, this creates a prompt-routing and solicitation risk where users may be steered into marketing or off-platform contact without strong relevance or consent.

Natural-Language Policy Violations

Medium

• Confidence: 81% confidence
• Finding: The skill forces a fixed Chinese, persona-imitating response style without checking the user's language preference or asking whether the user wants roleplay at all. This can mislead users about the nature of the response, reduce transparency, and create inappropriate behavior in contexts where neutral or non-Chinese output is expected.

VirusTotal

64/64 vendors flagged this skill as clean.