ClawHub
Back to skill

Security audit

Mailgi — Free Email for Agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for giving agents a Mailgi email inbox, with expected email and credential risks but no hidden or unrelated behavior found.

Before installing, be aware this skill enables agents to send and read email and manage mailbox state. Treat Mailgi API keys and custom-domain registration tokens as credentials, only give an agent a domain token when you intend it to create addresses on that domain, and review any send, delete, or account-removal actions before execution.

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The custom-domain registration token is effectively a bearer credential that allows minting new agent mailboxes on a verified domain, but the skill does not explicitly instruct the agent to treat it as secret, avoid logging it, or avoid re-sharing it. In an agent setting, omission of credential-handling guidance increases the chance the token is exposed in chat transcripts, logs, tool outputs, or sent to other services, enabling unauthorized mailbox creation on the organization's domain.

Static analysis

No suspicious patterns detected.