ClawHub
Back to skill

Security audit

VerifiedEmail

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a normal VerifiedEmail connector, with only a scoping note about when agents should invoke it.

Install only if you intend your agent to use VerifiedEmail and are comfortable sending the email addresses you ask it to verify to that service. Keep any API credentials scoped to VerifiedEmail and review requests before using the skill on sensitive contact lists.

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
94% confidence
Finding
The manifest description says to use this skill for ANY VerifiedEmail request and instead of calling the API directly, which is an overly broad routing trigger. This can cause the agent to invoke the skill in situations outside its narrowly documented read/search scope or when safer, more context-appropriate handling should be chosen, increasing the chance of unintended external data access or action execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.