ClawHub

以文言文压缩输出、节省 token。当用户要求文言回复、节省 token、省输出时触发。支持三档：极致(/e/Extreme)、适度(/m/Medium)、轻微(/l/Light)。

Security checks across malware telemetry and agentic risk

Overview

This is a text-formatting skill that compresses responses into Classical Chinese and does not include code execution, data access, network use, or persistence.

Install this only if you intentionally want shorter Classical Chinese-style answers. Use light compression or disable the skill for medical, legal, security, debugging, or other situations where precise wording and readability matter.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation text is broad enough that ordinary requests such as asking to save tokens, shorten output, or reply in classical Chinese could trigger the skill in contexts where the user did not clearly intend persistent stylistic transformation. That can cause unintended mode switching, reduced clarity, and interference with normal assistant behavior across unrelated tasks.

Natural-Language Policy Violations

High
Confidence
94% confidence
Finding
The skill directs output into Chinese/classical Chinese by default without requiring explicit user language consent beyond broad trigger phrases. In safety-sensitive, technical, or multilingual contexts, forced compression and language switching can degrade comprehension, obscure warnings, and increase the chance that the user misunderstands critical instructions or system responses.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal