ClawHub
Back to skill

Security audit

189mail-daily-fetch

Security checks across malware telemetry and agentic risk

Overview

The skill does what it says: logs into a 189.cn mailbox, downloads the newest email, and saves it locally, but users should treat the credentials and exported email file as sensitive.

Install only if you intentionally want an agent to access your 189.cn mailbox. Provide credentials only in a trusted session, confirm before setting up any daily schedule, and consider asking it to save EML files in a private folder instead of the Desktop.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes very broad phrases such as '189邮箱' and 'fetch latest email', which can cause the skill to activate for ambiguous user requests that do not clearly indicate consent to log into an email account and download private content. In this context, unintended invocation is risky because the skill performs sensitive actions involving credentials, mailbox access, and saving email contents to a local desktop path.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes saving the downloaded email to the desktop without a prominent warning that desktop storage may expose sensitive email contents to other local users, backups, indexing services, or shoulder-surfing. Because the skill handles raw EML files from a personal mailbox, the lack of a clear warning and consent around the storage location increases the chance of accidental data disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.