ClawHub

日语到中文翻译器

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Japanese-to-Chinese translation skill with no code, installs, credentials, persistence, or hidden behavior found.

Before installing, make sure you want a skill that may activate for Japanese business/legal translation and generally produces Chinese output. For confidential contracts, LOIs, NDAs, or reports, confirm the target language and be comfortable with how your agent and model provider handle document contents.

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
95% confidence
Finding
The trigger list is overly broad and mixes generic phrases like '翻译', '日语文件', and document-type keywords such as 'LOI', which can cause the skill to activate in contexts where the user did not specifically request this translator. In an agent environment, unintended invocation can route sensitive business or legal documents into the wrong workflow, causing privacy, integrity, or task-selection errors.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill is designed to always translate Japanese into Chinese and frames Chinese output as the default without requiring the user to confirm output language or locale. This can lead to incorrect or unsafe handling of multilingual legal or commercial content when the user expected another target language, a summary, or source-language preservation, especially in high-stakes document workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal