Question Type Generator

Security checks across malware telemetry and agentic risk

Overview

This is a simple educational prompt skill for generating higher-math practice questions, with no code execution, credentials, persistence, or external data access.

This appears low risk to install as an instruction-only math practice generator. The main things to consider are practical rather than security-related: it may activate on general math-practice requests, and non-Chinese users should confirm the generated questions and solutions are understandable and accurate.

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests for math practice, which can cause the skill to activate unexpectedly instead of only when explicitly invoked. This is mainly a scope and routing issue rather than a direct security exploit, but it can override user intent, cause prompt collisions with other skills, or expose the agent to unintended behavior chaining.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill is written entirely in Chinese and implicitly constrains interaction/output to that language without stating any user-choice mechanism. This can lead to poor user experience, misinterpretation of requests, or unsafe task execution if users receive content they cannot verify, though it is not an inherently malicious pattern in this educational context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal