ClawHub
Back to skill

Security audit

Apple Health

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local Apple Health export analysis workflow, with sensitive-data and third-party package risks users should understand before use.

Install only if you trust the third-party MCP package and the MCP client that will receive query results. Point HEALTH_DATA_DIR only at the specific export folder you want analyzed, prefer bounded queries, avoid raw-row output unless needed, and periodically review or delete ~/apple-health because it may contain sensitive paths and health summaries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Unbounded Resource Access

Medium
Category
Excessive Agency
Content
- Assuming live HealthKit access from CLI agents -> setup fails because only exported data is available
- Using wrong export path in MCP env -> server starts but returns no data
- Running SQL before schema discovery -> queries fail on wrong table names
- Unbounded queries on large exports -> slow analysis and noisy output
- Reporting "today" metrics from stale export -> inaccurate recommendations
- Running MCP package on non-LTS Node -> DuckDB native module errors can break startup
Confidence
80% confidence
Finding
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.