ClawHub
Back to skill

Security audit

邮件技能

Security checks across malware telemetry and agentic risk

Overview

This SMTP email skill is mostly coherent, but it asks for broad local command and file authority while handling email credentials and outbound messages without enough scoping or user-control safeguards.

Review before installing. Use environment variables or a secrets manager instead of email_config.json, keep any SMTP app password scoped and revocable, require explicit confirmation before sending or bulk sending, and avoid letting user-provided text become shell commands or attachment paths without validation.

SkillSpector

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
92% confidence
Finding
The skill advertises the powerful `exec` tool while claiming command execution is limited to a whitelist, but it does not actually document or enforce any such whitelist for this email skill. That mismatch can mislead users and downstream agents into trusting unsafe command execution paths, increasing the chance of arbitrary local command execution if user-controlled input is later passed into shell commands.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrase says to use the skill whenever the user needs email-related functionality, which is overly broad for a skill that exposes `read`, `write`, and especially `exec`. Overbroad routing can cause the agent to invoke this skill in unintended contexts, expanding the attack surface and potentially enabling unsafe file or command operations beyond simple email sending.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to create a plaintext `email_config.json` containing SMTP username and password, which creates a straightforward credential exposure risk through local file disclosure, accidental commits, backups, or shared workspaces. In an agent context with `read`/`write` capabilities, storing live mail credentials in predictable local files is especially risky because other tools or sessions may access or leak them.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.