Back to skill

Security audit

Apple Mail (MacOS)

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent controlled access to Apple Mail, but its mail actions are disclosed, local, and guarded by dry-run and confirmation requirements.

Install only if you want an agent to operate Apple Mail on your Mac. Keep the default dry-run and confirmation gates enabled, review recipients and message counts before any send/delete/bulk action, and remember that local operation logs may record mail metadata and high-risk action history.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The document explicitly instructs use of Mail.app for send, move, archive, and delete actions but provides no guardrails such as confirmation requirements, dry-run guidance, scope checks, or warnings about privacy and irreversible mailbox changes. In an agent skill, this increases the chance of unintended destructive actions or disclosure of sensitive email content because the operational path normalizes high-impact mail manipulation as routine.

Static analysis

No suspicious patterns detected.