ClawHub
Back to skill

Security audit

macOS AppleScript Fallback (Reminders / Notes / Calendar / iMessage)

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it says, but it can send real iMessages and create persistent Apple app data without a required final confirmation step.

Install only if you are comfortable letting an agent control Apple Reminders, Notes, Calendar, and Messages on your Mac. Before any run, manually confirm the recipient, message body, dates, calendar, and note account, and avoid granting Full Disk Access unless you have a specific need and understand the wider access it gives.

SkillSpector

By NVIDIA
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 (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is explicitly designed to send iMessages on the user's behalf, but the instructions do not require an explicit confirmation or warning immediately before message transmission. That creates a meaningful risk of unintended outbound communication, privacy leakage, or social harm if the agent misinterprets the user's request or uses an incorrect recipient.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The troubleshooting guidance tells users to enable Automation access for multiple apps and potentially Full Disk Access, but it does not clearly warn that these permissions grant broad control over personal data and system behavior. In a skill designed to automate Reminders, Notes, Calendar, and Messages through osascript, this increases the blast radius if the skill is misused, modified, or invoked in an unintended context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script causes the Messages app to send an iMessage immediately once invoked, with no interactive confirmation, recipient verification, or policy check inside the script itself. In an agent-skill context, that creates a real risk of unintended outbound communication, social-engineering abuse, or privacy leakage if the caller supplies the wrong target or message.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.