ClawHub
Back to skill

Security audit

Apple Reminders

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Apple Reminders helper, with expected reminder-management powers but limited warnings around delete commands.

Before installing, be aware this skill can help an agent change and delete Apple Reminders on a Mac after Reminders permission is granted. Use deletion commands only after confirming the target reminder ID or list name, especially commands using --force or --delete.

A.I.G

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

SkillSpector

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
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill documents a forceful reminder deletion command without any warning that the action is irreversible or that users should confirm the target item before running it. In an agent or copy-paste workflow, this increases the chance of accidental permanent data loss, especially because `--force` implies bypassing safeguards.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill describes deleting an entire reminders list but does not warn that this can remove a collection of user data and may have broader impact than deleting a single reminder. Because the skill is designed for direct task execution, omission of a warning makes accidental destructive use more likely.

Static analysis

No suspicious patterns detected.