口播脚本打磨

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  0.1.0

Overview

This is a low-risk Chinese spoken-script polishing skill with no code execution, credential use, or hidden access requests.

This appears safe to install for Chinese spoken-script polishing. Review rewritten scripts for factual accuracy and intended tone before publishing, and avoid submitting confidential drafts unless you are comfortable with your agent processing them.

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: 89% confidence
• Finding: The skill’s operational instructions are primarily in Chinese without an explicit language-choice mechanism or opt-in, which can cause users or downstream agents to misunderstand the skill’s purpose, constraints, or safe usage requirements. While this is not an exploit primitive by itself, language opacity can increase the chance of misuse, incorrect execution, or failure to notice important limitations in multilingual environments.

VirusTotal

64/64 vendors flagged this skill as clean.