ClawHub
Back to skill

Security audit

macOS Reminders

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it manages local macOS Reminders, with a disclosed local action log that users should be aware of.

Install only if you are comfortable granting local AppleScript automation access to Reminders.app. Be aware that created reminder names and list names are written to a local log under the skill directory; avoid using it for highly sensitive reminders unless you are comfortable with that local retention.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger phrases are broad enough to capture many ordinary requests involving reminders or to-dos, which increases the chance of the skill being invoked in unintended contexts. Because the skill performs local automation actions, overbroad activation can lead to privacy-sensitive data being sent to scripts or reminders being created without sufficiently precise user intent.

Ssd 3

Medium
Confidence
93% confidence
Finding
The skill instructs that all actions are logged with timestamp, command, list, and name, which means user reminder content and related metadata may be persistently stored. Reminder titles and list names often contain sensitive personal or work information, so unconditional logging creates unnecessary privacy exposure and potential retention risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal