Mailscope Email Detection

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 9:48 AM UTC
• Version:
  0.1.0

Overview

This skill does what it claims: it uploads a user-selected email file to a Mailscope service for security analysis, but users should understand that the email contents leave their machine.

Install only if you are comfortable sending the full email file, including headers, recipients, body content, links, and attachments, to the Mailscope service at https://x.lizhisec.com. Do not use it on confidential, regulated, or third-party-sensitive emails unless that upload is allowed by your policy. Keep the API key in config.json private.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The script transmits the entire .eml file, which can contain highly sensitive content such as message bodies, attachments, headers, recipient lists, and authentication artifacts, to a third-party remote service. In the context of an email-security skill this behavior is functionally expected, but the lack of an explicit user warning/consent step creates a real privacy and data-handling risk, especially for confidential or regulated emails.

VirusTotal

65/65 vendors flagged this skill as clean.