ClawHub

Smart Nutrition Customizer

Security checks across malware telemetry and agentic risk

Overview

This is a plain nutrition-planning skill that asks for expected body metrics to calculate calories and meals, with no code execution, persistence, or data export found.

Install only if you are comfortable sharing body metrics and dietary restrictions with the agent for meal planning. Treat the output as general nutrition guidance, not medical advice, and avoid using it for medical conditions, eating disorders, pregnancy, severe allergies, or clinical diet needs without a qualified professional.

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
88% confidence
Finding
The trigger phrases are broad enough to activate on many ordinary nutrition-related requests, which can cause the skill to intercept user queries outside a clearly bounded scope. In a health-adjacent context, over-triggering increases the chance the agent will provide calorie or diet guidance when the user did not explicitly ask for this workflow, creating privacy and safety concerns.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill requests body and health-related attributes such as age, weight, height, gender, activity level, and dietary restrictions without any privacy notice, data-minimization guidance, or medical disclaimer. This is dangerous because it normalizes collection of sensitive personal data in a health-related workflow and may lead users to rely on generated plans as medical advice without understanding the limitations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal