ClawHub
Back to skill

Security audit

Tmp.RvNip39MEs

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent Apple-app automation, but it asks users to install an external native MCP with broad access to sensitive local data and message-sending or deletion powers without clear confirmation boundaries.

Review this before installing if you use Apple Mail, Messages, Photos, Notes, Calendar, Reminders, or Contacts with sensitive data. Prefer installing only if you trust the publisher and release binary, and require explicit confirmation before sending messages, sending email, deleting records, exporting photos, or granting Full Disk Access for Messages history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger language is broad enough to capture many common requests involving personal Apple app data and actions, which can cause the skill to activate in situations where the user did not intend powerful native-app automation. In this context, the skill can read sensitive data and perform side effects such as sending messages or modifying records, so overbroad routing increases the chance of unintended privacy exposure or destructive actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises capabilities to send mail/messages and create, update, delete, import, export, and read highly sensitive personal data, but it does not clearly warn about these high-impact operations or indicate that explicit confirmation should precede them. Because the skill spans Mail, Messages, Notes, Photos, Calendar, Reminders, Contacts, and direct chat history access via chat.db, insufficient warnings materially raise the risk of unauthorized disclosure, unintended communications, and destructive changes.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.