ClawHub
Back to skill

Security audit

Email Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed email-sending skill, but users should be careful because it can send attachments and requires email credentials.

Install only if you intend to let the agent send email through your SMTP account. Use an app password or dedicated email account, keep email_config.json out of version control, and manually verify recipients, body text, and attachments before any send command.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The documentation gives contradictory security-relevant guidance about authentication: one section says no extra API key is required because SMTP auth is used, while the known limitations section says the skill cannot be used without an API key. This inconsistency can mislead operators about what credentials are needed, causing insecure setup workarounds, failed deployments, or accidental disclosure of unrelated secrets while troubleshooting.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The capability coverage text is excessively broad and ambiguous, including generic communication and notification scenarios rather than tightly constraining when the skill should activate. In an agent environment, this can cause over-triggering for loosely related prompts and lead the agent to prepare or send emails in contexts the user did not explicitly intend.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This skill enables outbound email and attachment transmission but does not prominently warn users about the risks of sending data to external recipients. In practice, that increases the chance of accidental data exfiltration, privacy breaches, or sharing sensitive attachments with the wrong destination, especially in automated or agent-driven workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.