ClawHub

文言

Security checks across malware telemetry and agentic risk

Overview

This skill only changes the assistant’s writing style to classical Chinese and does not add code execution, credential access, file access, or network behavior.

Install this only if you want the assistant to answer in classical Chinese by default. Disable it or ask for plain language when clarity matters, especially for safety, legal, medical, financial, or technical instructions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill enables implicit invocation without any activation constraints, so it may be applied automatically in contexts where the user did not request classical Chinese output. That can silently alter responses, reduce clarity, and interfere with safety-critical or high-precision interactions by transforming the assistant's communication style without informed user consent.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The default prompt forces replies into classical Chinese by default, with no indication of user choice or opt-in. This can degrade usability, obscure important instructions or warnings, and create misunderstanding in general Q&A, coding help, or daily-work scenarios where precise modern language is necessary.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The file defines only Wenyan response registers and does not indicate any user opt-in, fallback behavior, or preservation of the user's original language preference. In a general-purpose Q&A and coding-help skill, this can override expected communication norms, reduce clarity for many users, and create accessibility/usability failures that materially affect safe and correct use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal