ClawHub
Back to skill

Security audit

Gmail Attachment Downloader

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it reads Gmail through IMAP and saves matching attachments locally, but users should handle the Gmail app password and downloads carefully.

Install only if you intentionally want Gmail attachments downloaded. Use a dedicated Gmail app password, avoid pasting it where it may be logged, prefer narrow sender/date/file-type filters or dry-run first, choose a dedicated download folder, and review attachments before opening them.

SkillSpector

By NVIDIA
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)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill asks for a Gmail app password and shows passing it via command-line arguments or environment variables, but it does not include an explicit warning about sensitive credential handling. Credentials supplied this way may be exposed through shell history, process listings, logs, or agent traces, and the skill context is more dangerous because it targets a live personal/business mailbox and bulk-downloads attachments.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill enables implicit invocation while advertising a broad, natural-language trigger for downloading Gmail attachments into a local folder. Because this capability accesses email content and writes files locally, an overly broad automatic trigger increases the chance of unintended activation, causing unauthorized mailbox access, unexpected data exfiltration, or unreviewed file downloads.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.