ClawHub
Back to skill

Security audit

Send AgentMailer Email

Security checks for vulnerabilities and agentic risk

Overview

This skill does sensitive email work, but its artifacts clearly describe that purpose and include user-authorization rules for sends, deletes, and other mailbox changes.

Install this only if you want an agent to manage AgentMailer email, including sending, scheduling, labeling, and deleting messages. Before use, make sure the agent shows or confirms recipients, subject, content, and destructive effects whenever the request is not exact, especially for bulk, BCC, reply-all, legal, financial, scheduled, or deletion actions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest advertises impactful mutating actions, including sending and deleting email, without any visible user-facing warning or safety notice about irreversible or externally visible effects. In this context, the absence of warnings makes accidental misuse more likely and reduces the chance a user understands that the skill can perform sensitive communications and destructive mailbox changes.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · agents/openai.yaml (reported line 11)May include surrounding context.

yaml
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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation for a capability that can send, forward, label, schedule, and delete email, but provides no trigger constraints or approval boundaries in the manifest. This increases the chance that the agent invokes the skill in response to vague user input or prompt-injected context, leading to unintended outbound communication or destructive mailbox actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.