health-sync

Security checks across malware telemetry and agentic risk

Overview

This skill handles sensitive health data and provider credentials, but the access is disclosed and matches its health-sync analysis purpose.

Install only if you trust the health-sync npm package and are comfortable storing provider tokens and a local health database on the agent host. Keep workspace/health-sync/.health-sync.creds and health.sqlite protected, prefer the encrypted bootstrap flow, avoid pasting raw secrets in chat, and remove local credentials/data when no longer needed.

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 (1)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger scope includes very broad phrases such as questions about sleep, recovery, training, activity, or 'your health', which can cause the skill to activate for generic health conversations unrelated to this tool. That increases the chance the agent unnecessarily accesses local health data or initiates sync operations when the user did not explicitly request cross-provider analysis, creating privacy and least-privilege concerns.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal