ClawHub

Weight Management 体重管理

Security checks across malware telemetry and agentic risk

Overview

This weight-management skill stores health tracking data locally with disclosed permissions and no evidence of hidden network, persistence, or destructive behavior.

Install only if you are comfortable letting it process weight, meal, steps, sleep, and possibly chat-history data. Choose a dedicated local storage folder, keep optional food-recognition/API features disabled unless you trust the provider, and confirm before allowing it to write health records.

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
86% confidence
Finding
The trigger list includes very broad everyday phrases such as '早餐', '午餐', '晚餐', '运动', and '今天吃了', which can cause accidental invocation during normal conversation. In a skill with declared file read/write and session access, unintended activation can lead to unwanted processing, retention of personal health data, or unexpected writes to local files even without malicious user intent.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The example trigger phrases are extremely close to ordinary conversational text such as meal logging and daily health chat, which can cause the skill to activate unintentionally during normal conversation. In a skill with file read/write and chat-history access, accidental activation can lead to unintended collection, persistence, or processing of sensitive health data without clear user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal