Xiaozhi Math Word Problem Coach

Security checks across malware telemetry and agentic risk

Overview

This is a math word-problem coaching skill made of Markdown guidance only, with no evidence of hidden execution, data access, or unsafe behavior.

Safe to install for math tutoring use. Be aware it may steer many word-problem or equation-setting requests into a Socratic coaching style instead of giving direct answers, and review any separately installed companion learning-profile skills if you care about educational progress records.

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
92% confidence
Finding
The skill declares mandatory activation for a very broad set of scenarios involving word problems, modeling, or setting variables, which can cause it to override more appropriate skills or routing logic. This is dangerous because overly broad invocation rules can lead to unintended skill execution, reduced system predictability, and prompt-routing abuse if many normal math requests are forcibly funneled through this skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal