Back to skill

Security audit

iCloud Mail

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses its mailbox access and optional automation, with explicit user approval required for consequential actions.

Installing connects a fully accessible mailbox through Maton and requires a local bridge. Confirm the mailbox and recipients before changes, and review every ongoing automation and destination. Use a separate Maton account with only necessary connections for hosted code. Resolve the documented network-policy incompatibility before enabling automation. Remove unused automations and revoke the app-specific password when finished. Manual review addressed the material scanner gaps, but did not verify external runtime enforcement.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep