Lesson

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward meal-planning skill that uses bundled recipe data and user-provided food preferences without evidence of hidden access, persistence, or unsafe behavior.

Safe to install for meal-planning use. Be aware it may activate on short food/menu-related phrases, so provide clear cooking context and avoid sharing sensitive personal health details unless needed for dietary guidance.

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: 80% confidence
Finding: The trigger phrases include very broad everyday expressions such as '今天吃什么' and '菜单', which can cause the skill to activate in conversations where the user did not clearly intend to invoke it. While this is not a direct code-execution issue, overbroad invocation can lead to unintended context capture, user confusion, and incorrect routing to the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal