ClawHub
Back to skill

Security audit

Apple Health Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Apple Health and fitness API skill, but users should understand it sends sensitive health-related data to Transition's external service.

Install only if you are comfortable sharing Apple Health-derived fitness data, profile information, and coach messages with Transition. Protect and rotate the API key, review Transition's privacy and deletion controls, and avoid sending unnecessary medical or personal details in prompts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Description-Behavior Mismatch

Medium
Confidence
85% confidence
Finding
The README presents the skill as Apple Health analytics, but prominently advertises unrelated workout-generation and training-plan capabilities. This scope expansion matters because users may authorize access expecting passive health insights while the service also supports broader coaching/generation behaviors that can transmit or process sensitive health context in ways not clearly disclosed.

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
Advertising AI coach, adaptation, and generation features goes beyond the stated Apple Health data query/analytics purpose and increases the chance that sensitive user data will be used for decisioning or generative outputs without clear boundaries. In a health-data context, undeclared capability creep is security-relevant because it weakens informed consent and can broaden data exposure.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README instructs users to connect personalized Apple Health data and provide an API key, but it does not include a clear warning that highly sensitive health data may be transmitted to a third-party API for processing. In this context, omission of privacy and data-handling disclosure is dangerous because users may unknowingly expose regulated or intimate health information.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly states that Apple Health data is synced to an external AI service and that the AI coach has full context on workouts and health metrics, but it provides no explicit privacy warning, consent guidance, data minimization notes, or retention/sharing disclosure. Because Apple Health data can include highly sensitive health and behavioral information, omitting a clear warning materially increases the risk of users exposing regulated or intimate personal data without understanding the consequences.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -X POST -H "X-API-Key: $TRANSITION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message": "How has my resting heart rate changed over the last month?"}' \
  "https://api.transition.fun/api/v1/coach/chat"
```

Example questions:
Confidence
96% confidence
Finding
This authenticated coach-chat request sends a user's natural-language query about personal health trends to an external AI service and the documentation states the service has full context on the user's Apple Health data. In the context of a health skill, this is a meaningful data transfer of sensitive personal information to a third party, and the lack of explicit privacy, minimization, and consent controls makes the transmission dangerous.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -H "X-API-Key: $TRANSITION_API_KEY" \
  "https://api.transition.fun/api/v1/workouts?start=2026-02-09&end=2026-02-15"
```

**Parameters:**
Confidence
93% confidence
Finding
The workouts endpoint retrieves user-specific workout history from an external service using an API key, which means the user's exercise records are stored and accessed outside the local Apple Health environment. In a health-data context, this creates privacy and exposure risk if users are not clearly warned that their personal fitness history is being transmitted to and retained by a third party.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -H "X-API-Key: $TRANSITION_API_KEY" \
  "https://api.transition.fun/api/v1/performance/pmc"
```

### Performance Stats
Confidence
91% confidence
Finding
The PMC endpoint exposes derived fitness/fatigue/form metrics calculated from Apple Health workout data via a remote service. Even though these are derived values rather than raw records, they still reflect sensitive health and training state, so transmitting and storing them externally without prominent disclosure increases privacy risk.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -H "X-API-Key: $TRANSITION_API_KEY" \
  "https://api.transition.fun/api/v1/performance/stats"
```

### Athlete Profile
Confidence
91% confidence
Finding
This endpoint returns performance statistics such as threshold paces, heart rate zones, and related metrics derived from the user's health/workout records through a third-party API. These analytics reveal sensitive physiological and fitness information, and the skill does not present adequate warning or consent language about external processing of such data.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -H "X-API-Key: $TRANSITION_API_KEY" \
  "https://api.transition.fun/api/v1/profile"
```

### Chat History
Confidence
95% confidence
Finding
The athlete profile endpoint likely exposes account-level user profile information associated with Apple Health-derived data through an external service. Profile and health-linked metadata can be highly identifying, so documenting access to this remote profile without clear privacy safeguards or user warning is a real privacy vulnerability in this skill context.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -H "X-API-Key: $TRANSITION_API_KEY" \
  "https://api.transition.fun/api/v1/coach/history"
```

## Rate Limits
Confidence
96% confidence
Finding
The chat history endpoint exposes prior AI conversations about the user's health and fitness, which can contain highly sensitive medical, behavioral, and lifestyle inferences. Storing and retrieving this history from a third-party service materially increases privacy risk, especially because the skill does not disclose retention or secondary-use practices.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.