ClawHub
Back to skill

Security audit

Mailcoach

Security checks across malware telemetry and agentic risk

Overview

This Mailcoach skill is purpose-aligned and disclosed, but users should review write and delete actions carefully before use.

Install only if you intend to let the agent manage your connected Mailcoach account. Confirm exact targets and payloads before any subscriber or list changes, be especially careful with delete/unsubscribe actions, and review the oo CLI install step before allowing it on a new machine.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The skill description says to use this skill for ANY Mailcoach request and instead of calling the API directly, which is an overly broad routing rule. This can cause the agent to invoke the skill on simple mentions of Mailcoach or on tasks where direct handling would be safer or more appropriate, increasing the chance of unintended read/write/destructive operations being selected.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.