Chinese Script Check Skill

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:22 PM UTC
• Version:
  0.1.0

Overview

This is a focused Chinese script proofreading skill, but it writes review notes to local files that may contain sensitive story details.

Install and use this skill in a dedicated folder, especially for confidential or unpublished scripts. Before running it, check whether character_check.txt, scene_check.txt, or QUESTION.md already exist, and delete the generated files when you no longer need the review notes.

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)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly instructs the agent to create local intermediate files without notifying the user or obtaining consent. Silent filesystem writes can unexpectedly persist sensitive script content, create privacy and data-retention issues, and may overwrite existing files depending on runtime behavior.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: Writing final results to QUESTION.md without disclosure introduces the same persistence risk, with added potential for overwriting an existing file and leaving behind potentially confidential editorial analysis. Because the write is part of the required workflow, a user could trigger persistent local changes without realizing it.

VirusTotal

64/64 vendors flagged this skill as clean.