ClawHub
Back to skill

Security audit

CN to EN Listing Writer

Security checks across malware telemetry and agentic risk

Overview

This is a simple writing skill for turning product details into Amazon listing copy, with no code, installation behavior, persistence, or sensitive access.

Installers should expect this skill to shape responses around Amazon listing copy when product-description or ecommerce-translation prompts match its triggers. Review generated claims for Amazon policy accuracy and factual support before publishing, especially warranty, certification, and compliance language.

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 trigger list includes generic ecommerce phrases like 'listing translation' and 'cross-border seller' that may cause the skill to activate in ordinary conversations not explicitly asking for this tool. Over-broad activation increases the chance of unintended routing, causing the agent to apply this skill in contexts where its assumptions, output style, or embedded links are not appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.