ClawHub

Ultrahuman Analytics

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Ultrahuman reporting skill that handles sensitive health data, but its behavior is disclosed and aligned with its purpose.

Install only if you trust the configured Ultrahuman MCP connection. Before use, confirm the email account and date range, understand that sleep, recovery, HRV, movement, and possible glucose data may be retrieved and summarized, and treat outputs as informational rather than medical advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger set is very broad ('use for any multi-day analysis, prediction, correlation, or export from Ultrahuman ring/CGM data'), which can cause the skill to be invoked in situations the user did not clearly intend. Because the skill accesses sensitive health-related metrics, over-invocation raises the chance of unnecessary processing or disclosure of personal data in contexts where a narrower skill or a direct answer would have been more appropriate.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs use of email from an environment variable or the user message to retrieve Ultrahuman metrics, but it does not require a clear user-facing notice or confirmation that sensitive health data will be accessed and aggregated. In a health-data context, silent retrieval and analysis of ring/CGM information increases privacy risk, especially if the email is sourced implicitly from environment state rather than an explicit current user action.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal