Security audit

163 Email Monitor

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed 163/126/yeah.net email helper, but it can access private mail and send messages or attachments, so it should be used carefully.

Install only if you trust this skill with the configured mailbox. Use a revocable mail authorization code, protect the .env file, and review the recipient, subject, body, and every attachment path before allowing any send command.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill advertises and instructs use of file reads and network access, including loading credentials from a local .env file and connecting to IMAP/SMTP servers, but does not declare permissions. Undeclared sensitive capabilities reduce transparency and consent, making it easier for a skill to access local secrets and transmit data off-host without clear user awareness.

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: The send command accepts arbitrary file paths from the caller and reads them from the local filesystem to attach and exfiltrate via email. In an agent-skill context, this creates a generic file-read-and-send primitive that exceeds narrow email-account operations and can be abused to leak sensitive local data if a user or upstream agent is tricked into supplying paths.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation text uses broad phrases like checking email, reading mail, sending email, or monitoring inbox, which can match many routine user requests. Over-broad triggers increase the chance the skill activates in unintended contexts, potentially causing unauthorized mailbox access, message retrieval, or email transmission when the user did not specifically intend to use this particular skill.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The usage section explains how to send email and attach files over SMTP but does not clearly warn that message bodies, recipients, and attachment contents will be transmitted to external mail servers. In a skill handling sensitive communications, missing disclosure can lead users to expose confidential local files or private content without informed consent.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: This command performs outbound email transmission, including optional attachments, immediately once invoked, with no confirmation gate or high-visibility warning about recipients and attached data. In an agent setting, that can turn prompt injection, user misunderstanding, or accidental invocation into unintended data exfiltration or misdelivery.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.