Xiaozhi Chinese Reading Decoder

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese reading-comprehension tutoring skill with disclosed study-tracking behavior and no executable code or hidden system access.

Before installing, expect this skill to activate frequently for Chinese reading passages or reading-comprehension questions. If connected to companion skills for learning records, material storage, or reminders, review what student work and progress notes may be saved.

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
90% confidence
Finding
The activation rules are written as mandatory and cover very common tutoring phrases, plus any time a user sends a reading passage or asks about reading comprehension. That can cause over-triggering, unintended routing, and overshadowing of more appropriate skills, reducing user control and making downstream behavior less predictable.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal