Back to skill

Security audit

ShellMail - Email Built for AI Agents

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ShellMail email-client skill with sensitive mailbox powers, but its access is purpose-aligned, scoped, and includes user-confirmation safeguards for destructive actions.

Install only if you trust shellmail.ai and intend the agent to manage a ShellMail inbox. Use it for agent-specific or disposable email rather than personal mail, review any token-saving command before approval, and require a fresh explicit confirmation before destructive actions like deleting a message or the entire address.

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.