职场高情商沟通润色/职场防背锅助手

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.0

Overview

This is a text-only Chinese workplace message polishing skill with no code, install steps, credentials, persistence, or external access.

Before using a generated workplace message, review the facts, tone, recipient context, and responsibility boundaries. Non-Chinese users may need to ask for translation or language adaptation because the skill’s template is written for Chinese output.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The skill hard-codes Chinese-only behavior and output formatting without offering a user language choice or documenting a necessary locale restriction. This can exclude users, cause misunderstanding when the user's environment or downstream tooling expects another language, and may lead to unsafe communication errors if the user relies on precise wording in multilingual workplace contexts.

VirusTotal

64/64 vendors flagged this skill as clean.