ClawHub

AI食品营养管理助手

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local nutrition diary skill that saves meal records and reports, with privacy considerations users should understand before use.

Install only if you are comfortable with meal history, nutrition estimates, and generated reports being stored locally in the skill’s user_data/report files. If you configure TianAPI, treat the API key as sensitive and remember that food lookup terms may be sent to that service.

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
93% confidence
Finding
The trigger list includes very broad everyday phrases such as '吃什么', '卡路里', and '今天吃了', which can cause the skill to activate in contexts where the user did not intend persistent nutrition tracking or analysis. Because this skill can save records and generate files, overbroad activation increases the chance of unintended data handling and confusing tool use.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs automatic saving of meal records and writing HTML reports, but it does not require clear, prior user consent or a transparent notice about what data is stored, where it is stored, and for how long. Since meal logs can reveal sensitive health and lifestyle information, silent persistence creates a meaningful privacy risk even in a benign nutrition context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal