ClawHub
Back to skill

Security audit

QQMail Organizer

Security checks across malware telemetry and agentic risk

Overview

This is a transparent QQ Mail management skill, but it should only be installed if you want an agent to access and manage that mailbox.

Install only if you intentionally want an agent to access your QQ Mail account. Use a dedicated QQ Mail authorization code, review dry-run JSON before applying rules, avoid broad delete or archive selectors, and require exact approval before any send, reply, archive, mark, or permanent delete operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill invokes shell commands, reads credentials from environment variables, accesses files for rules, and performs network operations over IMAP/SMTP, yet it declares no explicit permissions boundary. In an agent ecosystem, this creates a trust and enforcement gap: a parent agent or policy engine may treat the skill as lower-risk than it really is, allowing mailbox access and outbound email actions without appropriate review.

Tp4

High
Category
MCP Tool Poisoning
Confidence
81% confidence
Finding
The skill description emphasizes inbox organization and safety boundaries, but the documented commands also allow sending brand-new emails, creating folders, and permanently deleting messages. That mismatch is dangerous because agents or reviewers may authorize the skill for passive triage/cleanup while overlooking externally visible or destructive actions, increasing the chance of unintended data loss or unauthorized communications.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.