Zen+ Health

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed read-only Zen+ Health integration, but it can expose sensitive wellness information if used in shared or poorly scoped environments.

Install only if you trust Zen+ Health and your OpenClaw environment with wellness notifications, timeline, profile, and preference data. Store ZEN_API_KEY as a secret, keep ZEN_API_BASE_URL set to the official Zen+ Health API host, avoid exposing responses in shared chats or logs, and revoke or rotate the key if it may have been exposed.

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
88% confidence
Finding
The trigger conditions are very broad and match common, everyday language about stress, emotions, and self-care, which can cause the skill to activate in situations where the user did not explicitly request access to a third-party wellness service. Because this skill can access sensitive profile, timeline, and notification data, overbroad invocation increases the risk of unnecessary collection, display, or transmission of personal wellness information.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises access to notifications, timeline, profile, and wellness progress data, all of which may reveal sensitive mental-health-adjacent or behavioral information, but it does not clearly instruct the agent to warn the user or obtain consent before retrieving or presenting that data. In a wellness context, this omission is more dangerous because even seemingly routine activity history can expose private emotional state, habits, or treatment-related patterns.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal