ClawHub
Back to skill

Security audit

Emoji Translator

Security checks across malware telemetry and agentic risk

Overview

This skill is a local emoji translation helper with no evidence of hidden data access, persistence, or destructive behavior.

Install only if you want emoji translation to trigger from common emoji-related phrases. Avoid sending sensitive text for emoji conversion unless you are comfortable with the agent processing that text locally.

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
91% confidence
Finding
The trigger phrases are broad, generic, and overlap with normal conversational requests in both Chinese and English, which can cause the skill to activate when the user did not explicitly intend to invoke it. Ambiguous activation can lead to unexpected transformation of user content, confusion, or unintended handling of sensitive text in contexts where emoji insertion or translation is inappropriate.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.