ClawHub
Back to skill

Security audit

Mailtrap

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Mailtrap integration, but it needs review because one inbox-cleaning action deletes messages without being tagged for explicit confirmation under its own safety rules.

Review before installing. The integration is purpose-aligned, but users should treat `clean_inbox` as destructive and require explicit confirmation before it runs, despite the missing tag. Also verify the OOMOL CLI install source before using the one-time remote install commands.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.