Xiaozhi Math Concept Explainer

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 7:28 AM UTC
• Version:
  1.0.0

Overview

The supplied evidence points to a math-learning skill with an overbroad activation note, but no sensitive access, hidden behavior, persistence, or unsafe actions.

Install this if you want help with math learning or conceptual explanations. Be aware it may activate for broad math-help requests, so use a more specific skill or instruction when you need only computation, exam-answer checking, or a different tutoring workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill mandates activation for a very broad set of common math-learning phrases, which can cause over-triggering and unnecessary routing into this skill even when a narrower or more appropriate skill should handle the request. In agent systems, overly broad mandatory triggers can degrade policy adherence, reduce user intent matching accuracy, and create denial-of-service-like behavior against better-scoped skills by monopolizing common educational queries.

VirusTotal

64/64 vendors flagged this skill as clean.