ClawHub
Back to skill

Security audit

Send AgentMailer Email

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AgentMailer email-writing skill with clear authorization rules for sending, scheduling, labeling, and deleting email.

Install this only if you want an agent to manage AgentMailer messages for you. Review requests carefully before authorizing sends, forwards, scheduled delivery, or deletion, because those actions can affect external recipients or mailbox state.

SkillSpector

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)

External Transmission

Medium
Category
Data Exfiltration
Content
value: "agentmailer"
      description: "Draft, send, reply to, forward, label, schedule, and delete AgentMailer email"
      transport: "streamable_http"
      url: "https://api.agentmailer.ai/mcp"
policy:
  allow_implicit_invocation: true
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill allows implicit invocation for a high-risk capability that can send, forward, schedule, label, and delete email, but it defines no trigger constraints, exclusions, or user-confirmation boundaries. In practice, this can let an agent invoke outbound email actions based on loose conversational context, increasing the chance of unauthorized messaging, data exfiltration, or destructive mailbox changes.

Static analysis

No suspicious patterns detected.