Moneyhub Enterprise

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate Moneyhub Enterprise integration, but it enables broad authenticated financial-data and payment-related actions without clear approval or scope limits.

Install only if you trust both Membrane and Moneyhub Enterprise for the relevant financial data. Use a least-privilege account, review granted scopes, prefer a pinned CLI version where possible, and require explicit confirmation before any payment, create/update/delete, bulk, or raw proxy request.

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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The invocation description is broad enough to match many generic requests about Moneyhub-related data and workflows, which can cause the skill to activate in situations where the user did not clearly intend external financial-system interaction. In a financial-data context, over-triggering is riskier than usual because it may lead to unnecessary handling of sensitive records or unintended outbound actions.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill operates on highly sensitive financial information and supports authenticated external requests, but the documentation does not clearly warn that user data may be sent to Moneyhub Enterprise or accessed through Membrane-managed connections. Without explicit disclosure and consent-oriented guidance, users or downstream agents may initiate actions involving financial records without appreciating the privacy and security implications.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal