ClawHub
Back to skill

Security audit

Check AgentMailer Email

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only AgentMailer email skill with clearly disclosed mailbox access and no evidence of hidden execution, persistence, deletion, sending, or exfiltration beyond its stated service integration.

Install this only if you want the agent to read and summarize AgentMailer inboxes, drafts, threads, and requested attachments. Because implicit invocation is enabled, review which workspace or account the AgentMailer MCP connection can access before use, and avoid using it in contexts where email contents should remain out of agent workflows.

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 (2)

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: "Read and search AgentMailer inboxes, messages, threads, drafts, and attachments"
      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 allows implicit invocation with no trigger scoping or activation constraints, so an agent may call this email-reading capability automatically based on loose intent matching. Because the connected tool can read inboxes, threads, drafts, and attachments, this raises the risk of unintended access to sensitive mailbox content without explicit user confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.