Habit Tracker

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:30 PM UTC
• Version:
  1.0.0

Overview

This is a local habit tracker that stores and updates habit files on your computer, with no evidence of network access or hidden behavior.

Install only if you are comfortable with an assistant creating and updating local habit JSON files and optional Markdown review files. Avoid sensitive habit names if privacy matters, and use HABIT_DATA_DIR, --data-dir, or --output only with directories you intend the skill to read or write.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill clearly performs file writes and reads an environment variable (`HABIT_DATA_DIR`) but does not declare corresponding permissions. Undeclared capabilities are dangerous because they bypass user and platform expectations about what the skill can access or modify, especially when it can write persistent files and redirect output locations.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The documented purpose says the skill tracks habits locally, but the actual behavior also creates, archives, and writes reports to arbitrary user-supplied output paths and an Obsidian vault path. This mismatch is security-relevant because users may consent to a simple tracker while the skill can modify unrelated files or write into broader note directories, increasing the chance of unexpected file-system side effects.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger list contains generic phrases such as 'habit', 'streak', 'weekly review', and 'morning routine', which can appear in ordinary conversation and unintentionally activate the skill. Unintended activation matters here because the skill can write files, add or remove habits, and generate reports, so a casual message could lead to persistent local changes.

VirusTotal

67/67 vendors flagged this skill as clean.