ClawHub
Back to skill

Security audit

AgentMailer CLI

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for AgentMailer CLI use, but it enables automatic invocation for a broad email and account-management shell workflow without enough scoping for sensitive actions.

Install only if you want agents to operate AgentMailer from the shell. Keep the API key scoped as narrowly as possible, review commands before sends or administrative changes, prefer dry-run when available, and avoid relying on implicit invocation for billing, policy, webhook, or outbound-message operations.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill enables implicit invocation for a shell-operating CLI without any trigger constraints or narrowing conditions. That can cause the agent to invoke the tool in response to loosely related prompts, increasing the chance of unintended shell actions, data access, or external side effects in a high-capability email-management context.

Static analysis

No suspicious patterns detected.