Ultrahuman Biodata Assistant

ReviewAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill is coherent for answering Ultrahuman health-data questions, but it relies on a trusted MCP setup that can access sensitive biodata.

Use this skill only if you intentionally want your agent to retrieve and summarize Ultrahuman health data. Before enabling it, make sure the ultrahuman_mcp server is from a trusted source, configured for the correct account, and that you are comfortable with sleep, recovery, heart-rate, glucose, and related metrics appearing in agent conversations.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A general question about sleep or recovery could lead the agent to retrieve Ultrahuman account data.

Why it was flagged

The trigger scope is broad for health-related questions and may cause the agent to call Ultrahuman tools even when the user does not explicitly name the service.

Skill content
Use this skill whenever the user asks about their Ultrahuman data, last night's sleep, recovery score, HRV, steps, glucose, metabolic score, readiness, or wants a "morning brief" or comparison over several days—even if they don't say "Ultrahuman" explicitly.
Recommendation

Use this skill only if you are comfortable with Ultrahuman data being fetched for implied sleep, recovery, or readiness questions; ask the agent to confirm first if you want stricter control.

What this means

The agent may use Ultrahuman account credentials to access private health data for the configured account.

Why it was flagged

The skill depends on credentialed Ultrahuman account access using a token and email, even though the registry metadata lists no required environment variables or primary credential.

Skill content
The ultrahuman_mcp MCP server must be available and configured (ULTRAHUMAN_TOKEN and ULTRAHUMAN_EMAIL in the environment, or user provides email for the request).
Recommendation

Ensure the MCP server is configured with the correct account, least-privilege credentials if available, and no shared or unintended Ultrahuman account token.

What this means

The security of the integration depends on the external MCP server implementation and configuration.

Why it was flagged

The skill relies on a separately installed/configured MCP server that is not included in the provided artifacts.

Skill content
The ultrahuman_mcp MCP server must be available and configured
Recommendation

Use a trusted Ultrahuman MCP server source and review its permissions before connecting health data.

What this means

Sleep, recovery, heart-rate, glucose, and metabolic metrics may be retrieved through the MCP channel and shown in agent responses.

Why it was flagged

The skill routes sensitive health metrics through an MCP tool call using the user's email and date.

Skill content
Call ultrahuman_get_daily_metrics with the user's email and the relevant date
Recommendation

Confirm that the configured MCP server is trusted and that responses are only shared in conversations where you are comfortable exposing health data.