ClawHub
Back to skill

Security audit

Japanese Translation And Tutor

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward Japanese translation and tutoring skill with only a minor chance of activating on vague language-help requests.

Safe to install for Japanese translation and learning help. Be aware it may activate on vague requests like asking what text says; if that is inconvenient, use more explicit Japanese-language prompts or adjust activation wording.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill advertises broad trigger phrases such as "translate," "help me understand," and "what does this say," which are common in everyday conversation and may cause the agent to invoke this skill outside narrowly translation-specific contexts. Over-broad activation can lead to inappropriate routing, accidental disclosure of user-provided text to the skill, or interference with more suitable skills, even though the skill content itself is not overtly malicious.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.