Back to skill

Security audit

apple-icloud-mcp

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Apple/iCloud MCP integration, but it requires sensitive Apple credentials and can access or modify configured Apple account data.

Install only if you are comfortable giving a third-party npm MCP server access to the Apple services you configure. Prefer setting only the needed credentials, review the upstream package before use, and treat send/delete/update operations as account-impacting actions that should require explicit confirmation.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises very broad natural-language triggers such as 'what's on my calendar', 'schedule a meeting', 'check my iCloud email', 'directions to', and 'will it rain', which overlap with common assistant requests. This can cause the skill to activate in many routine contexts and expose highly sensitive capabilities across mail, contacts, calendar, and music without sufficiently narrow routing boundaries, increasing the risk of accidental invocation or over-collection of user data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.