ClawHub
Back to skill

Security audit

withings-health

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says by connecting to Withings to read health metrics, but users should treat its local OAuth token file as sensitive.

Install only if you are comfortable granting access to your Withings health data. Keep WITHINGS_CLIENT_SECRET, any .env file, and tokens.json private; do not commit or share the skill directory after authenticating. Delete tokens.json and revoke the Withings app authorization when you stop using the skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The skill is presented as a simple data-fetching capability, but it also performs OAuth authorization, token exchange, token refresh, and local token storage. That hidden operational scope matters because it introduces credential-handling and persistent secret-storage risks for highly sensitive health data, and users or operators may enable it without understanding those implications.

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The skill loads client credentials from a local .env file and persists OAuth tokens, including refresh tokens, to tokens.json on disk. Because this skill handles sensitive health data, storing long-lived credentials locally without access controls, secure storage, or clear disclosure increases the risk of credential theft and unauthorized API access if the host is shared or compromised.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill processes highly sensitive health information and uses OAuth credentials/tokens, yet the documentation does not warn about privacy risks, local token storage, or handling of medical-adjacent data. In this context, weak disclosure increases the chance of accidental overexposure, insecure deployment, or inappropriate sharing of sleep, weight, and body-composition data.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
saveTokens writes OAuth token material to a local JSON file in plaintext with no warning, masking, encryption, or permission hardening. A stolen refresh token can enable continued access to the user's Withings account and associated health data, which is particularly sensitive.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.