WHOOP Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it connects to WHOOP to retrieve user-authorized fitness and profile data, with sensitive-data cautions but no hidden or purpose-mismatched behavior found.

Install only if you are comfortable giving the agent read access to WHOOP health, workout, sleep, body-measurement, name, and email data. Keep ~/.whoop/credentials.json and ~/.whoop/token.json private, avoid using this on shared machines, be careful with --json output in logs or transcripts, and revoke the WHOOP OAuth grant when you no longer use the skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill handles OAuth client credentials, tokens, and highly sensitive health data, but the documentation does not give an explicit privacy and secure-storage warning. Users may unknowingly place secrets in predictable local paths or expose health data through raw JSON output, logs, backups, or shared machines.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: This script prints highly sensitive personal and health data, including name, email, user ID, height, weight, and heart-rate information, directly to stdout with no consent check, masking, or contextual warning. In an agent/skill environment, stdout may be surfaced to users, logs, transcripts, or calling systems, creating an avoidable privacy exposure even if the data access itself is legitimate.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal