Habit Tracker Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:30 PM UTC
• Version:
  1.0.3

Overview

This habit-tracking skill appears useful and purpose-aligned, but it handles sensitive routine and wellness data with unclear consent around persistence, automation, and sharing.

Review this before installing if you track health, sleep, work routines, or other private habits. Install only if you are comfortable with local storage of habit data, recurring automated check-ins, and any cross-tool integrations; disable or avoid integrations unless the skill clearly lets you opt in, revoke access, and delete stored data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The README explicitly advertises automatic daily outreach and cross-tool sync, but it does not clearly warn users that the skill may proactively send messages and share or derive habit-related data across tools. In an agent ecosystem, this can create unexpected privacy exposure, surprise messaging behavior, and consent issues because users may install the package without understanding the ongoing automation and data flows.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The setup prompt instructs the agent to run a shell script and create or modify multiple local JSON data files, but it does not require explicit user consent or disclose that personal habit data will be stored on disk. In an agent environment, silent local writes create privacy and transparency risks because users may reveal sensitive wellness, health, or routine information without realizing it is being persisted.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly supports cross-tool synchronization and makes completion data available to other tools, but it does not describe any consent model, access controls, data minimization, or privacy notice around that sharing. Because the tracked data includes health, wellness, routines, and behavioral patterns, silent or poorly scoped sharing can expose sensitive personal information across tools beyond what users reasonably expect.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The pattern-analysis section describes inference over sensitive behavioral and wellness data, including habit correlation, skip clustering, and sleep-related performance impacts, but provides no explicit user warning or informed-consent flow. Even if the feature is useful, generating and storing these inferences can reveal intimate lifestyle or health-adjacent information and increase privacy risk if accessed, shared, or retained indefinitely.

VirusTotal

64/64 vendors flagged this skill as clean.