Security audit

habit-tracker

Security checks for vulnerabilities and agentic risk

Overview

This habit tracker looks purpose-built, but it under-discloses that personal habit messages may be sent to SkillBoss while also claiming data is stored locally.

Install only if you are comfortable with habit-related prompts and personal routine details potentially being sent to SkillBoss for processing. Use a dedicated, revocable API key, avoid entering sensitive health or private routine information unless you accept that data flow, and review the external setup guide before following any additional instructions.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Intent-Code Divergence

High

Confidence: 98% confidence
Finding: The skill explicitly claims 'All data stored locally' while also showing habit-related user messages being sent to an external API. This is a real privacy and transparency issue because users may disclose sensitive behavioral or health-adjacent information under false assumptions about where their data is processed.

Context-Inappropriate Capability

Medium

Confidence: 87% confidence
Finding: The skill requires an API key and forwards user habit content to a third-party service, expanding data exposure beyond what users would reasonably expect from a simple habit tracker. While external NLP may support the feature set, the capability is insufficiently justified and not bounded, creating avoidable privacy risk.

Vague Triggers

Medium

Confidence: 80% confidence
Finding: Several trigger phrases such as 'new habit' or 'habit progress' are broad enough to match ordinary conversation, which can cause accidental invocation. In this skill, accidental triggering matters because it may result in unintended processing or transmission of user messages to an external service.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill description presents a local habit-tracking experience but does not clearly warn that user habit content may be sent to an external API. This omission undermines informed consent and increases privacy risk for potentially sensitive personal routine data.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The privacy/storage messaging is internally inconsistent: it says data is stored locally, then describes remote API-based natural language understanding. Conflicting messaging can mislead users into sharing sensitive habit and wellness information without understanding that it may be processed remotely.

Static analysis

No suspicious patterns detected.