ClawHub
Back to skill

Security audit

mx-financial-assistant

Security checks across malware telemetry and agentic risk

Overview

This financial assistant is coherent, but broad triggers and limited privacy/risk disclosure could send unintended questions to an external finance API and present investment-style outputs without enough caution.

Review before installing. Use it only when you intentionally want Eastmoney-backed financial Q&A, and avoid entering secrets, account identifiers, private holdings, non-public business information, or proprietary research unless you are comfortable sharing that text with the external API. Treat any stock, fund, or allocation output as informational rather than personalized financial advice.

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 (3)

Vague Triggers

Medium
Confidence
86% confidence
Finding
技能触发短语包含“帮我查一下”“请问”“分析一下”“总结一下”等高频通用表达，容易与普通对话重叠，导致在用户并未明确请求金融工具时被误触发。对一个具备网络访问和投资相关输出能力的技能而言，误触发可能造成无意的数据外发、错误路由以及在不适当上下文中给出投资建议样式的内容。

Missing User Warnings

Medium
Confidence
89% confidence
Finding
该技能面向“投资研究、资产配置、风险管理、理财决策、选股推荐”等场景，但描述中缺少醒目的风险披露与非投资建议声明。用户可能将输出误认为个性化、可直接执行的投资建议，从而在高风险金融场景中放大误导、合规和声誉损害。

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The script transmits raw user questions to a third-party remote API, but this file provides no disclosure, consent flow, or data-minimization guardrail before sending potentially sensitive financial or personal information. In a finance-oriented assistant, users may paste investment plans, account-related context, or proprietary research prompts, increasing privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.