Frontend Interviewer CN

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

Overview

This is a Chinese frontend interview coaching skill made of local markdown study materials, with no executable code or hidden data access.

Safe to install for Chinese-language frontend interview preparation. Be aware it may activate on generic interview or explanation prompts and may answer in Chinese by default; performance-topic coverage may be incomplete because the referenced performance.md file is missing.

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: 86% confidence
• Finding: The quick-trigger table includes very generic phrases such as “模拟面试”, “开始面试”, and “解释一下XXX”, which can easily appear in normal conversation and cause the skill to activate unintentionally. This creates routing ambiguity and may override user intent, especially in multi-skill environments where broad trigger matching can invoke the wrong capability without explicit consent.

VirusTotal

66/66 vendors flagged this skill as clean.