ClawHub
Back to skill

Security audit

163邮箱基础版

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed 163.com email helper skill, but users should treat its mailbox access and plaintext auth-code configuration as sensitive.

Install only if you are comfortable giving the agent access to your 163 mailbox. Use a client authorization code rather than your login password, keep ~/.config/email-163-com/config.json out of version control and backups where possible, set restrictive permissions such as chmod 600, and avoid using callback URLs or processing sensitive mail unless you trust the runtime handling it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
77% confidence
Finding
The skill handles highly sensitive email content and also documents a `callback_url`, but it does not prominently warn users that message bodies, sender/recipient metadata, attachments, and possibly search results may be transmitted to external systems or agent/runtime components. In an agent context with `exec`, `read`, and `write` tools, this omission increases the risk of unintended disclosure of personal or business email data.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documented configuration stores mailbox credentials/auth codes in plaintext JSON on disk. Even though the file mentions setting restrictive permissions later, the guidance is not prominent enough and plaintext credential storage can expose mailbox access to other local users, backups, logs, or accidental commits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.