ClawHub
Back to skill

Security audit

WHOOP Health

Security checks across malware telemetry and agentic risk

Overview

This WHOOP skill is a coherent, user-directed health-data integration, but users should treat the saved tokens and exported health files as sensitive.

Install this only if you intend to connect a WHOOP account. Review the read scopes during WHOOP consent, keep ~/.whoop_tokens.json private, avoid exporting profile or body-measurement data unless needed, store JSON/CSV exports somewhere secure, and run the documented revoke command when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill uses sensitive capabilities including network access, shell execution, environment variables, and local file read/write, but does not declare permissions or warn the user. This reduces transparency and can cause users or calling systems to authorize behavior they did not expect, especially because the skill handles OAuth tokens and health data.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
The description frames the skill primarily as data fetching and analysis, but the documented behavior also includes OAuth token acquisition/refresh/revocation, localhost callback handling, persistent token storage, and local export of sensitive data. This mismatch is dangerous because users may consent to analytics without understanding that credentials and health/profile data will be persisted and managed locally.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The trigger language includes broad phrases like requests to analyze wearable data, which may cause the skill to activate for generic health or wearable prompts beyond clear WHOOP-specific intent. Over-broad triggering can expose sensitive health workflows unexpectedly, leading to unnecessary authentication prompts, data access, or local storage when the user did not intend to use this integration.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill processes highly sensitive health and profile information and also stores OAuth tokens locally, but the description does not warn users about local persistence or export to JSON/CSV files. In the context of health data, this omission is especially dangerous because exported files and token stores may remain on disk, be backed up, or be accessed by other local processes.

Missing User Warnings

Medium
Confidence
79% confidence
Finding
The script handles sensitive health data and persists both tokens and fetched WHOOP data to local files without explicit privacy notice, consent language, retention guidance, or file-permission hardening. In the context of a health-data skill, silent storage of recovery, sleep, workout, profile, and body measurements increases privacy risk if the host is shared, backed up insecurely, or later compromised.

Credential Access

High
Category
Privilege Escalation
Content
## Token Management

Tokens are stored at `~/.whoop_tokens.json`. The fetch script auto-refreshes using the refresh token when the access token expires (24h lifetime).

To revoke access: `python3 scripts/whoop_auth.py --revoke`
Confidence
84% confidence
Finding
access token

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.