ClawHub
Back to skill

Security audit

163邮箱基础版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a basic 163.com email CLI guide whose sensitive email access is disclosed and aligned with its stated purpose.

Before installing, treat this as access to a real mailbox: use a 163 client authorization code rather than your login password, restrict the config file permissions, review recipient and attachment details before sending, and avoid exposing unnecessary email content in prompts or logs.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill invocation guidance is overly broad and tells the agent to execute tasks based on high-level user descriptions without clear guardrails. In an email-management skill with exec/read/write permissions, vague triggers can cause unintended sending, reading, or searching of sensitive email data in response to ambiguous prompts.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill handles mailbox credentials and message contents but does not prominently warn users that emails, attachments, and metadata may contain sensitive information that could be transmitted, displayed, or logged. Without a clear warning, users may unknowingly expose personal or business data through agent execution, terminal history, logs, or downstream systems.

Static analysis

No suspicious patterns detected.