Apple Health CSV

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 5:14 AM UTC
• Version: 1.0.0

Overview

This skill is a local Apple Health CSV analyzer; it handles sensitive health data, but I found no hidden sharing, persistence, or unsafe behavior.

Use this only for local Apple Health CSV exports you intentionally provide. Keep the export directory protected, avoid syncing or sharing raw CSVs and generated summaries unless you accept the privacy risk, and be aware that some displayed metric names are in Chinese.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill appears to rely on environment variables and local file access but does not declare any explicit tool scope or permissions boundary. In a skill that handles sensitive health data, undeclared file/env capabilities increase the risk of over-broad access, accidental data exposure, and make it harder for the agent platform to enforce least privilege.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation text is broad enough to trigger on many general health, fitness, sleep, or daily-summary requests, which may cause the skill to activate when not clearly needed. Because the skill processes highly sensitive personal health data, over-broad invocation raises privacy risk by encouraging unnecessary access to local health exports.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The setup and usage instructions describe handling and querying personal health exports without clearly warning that the data is sensitive medical/biometric information. Users or downstream agents may expose files, copy them into insecure locations, or share outputs too freely if the documentation does not emphasize privacy handling.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: This code defines user-visible metric names entirely in Chinese and later prints summaries and labels in Chinese, which imposes a specific language on users. The file does not provide any opt-in, configuration, or justification that this is a China-specific or Chinese-only tool, so it conflicts with the language/locale policy criterion.

Static analysis

No suspicious patterns detected.