ClawHub
Back to skill

Security audit

Wealth Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only personal finance guidance skill with no hidden execution or persistence, but users should treat its financial, tax, investment, and estate-planning output as educational.

Before installing, understand that this skill may ask you to discuss sensitive financial and estate details. Do not provide account numbers, passwords, SSNs, private keys, or beneficiary-identifying details unless truly necessary, and verify investment, tax, retirement, and estate decisions with qualified professionals in your jurisdiction.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README presents the skill as a comprehensive wealth advisor covering investing, tax optimization, retirement planning, estate planning, and alternative assets, but provides no warning that outputs may be incomplete, jurisdiction-specific, or unsuitable as professional financial, tax, or legal advice. Because these domains are high-impact and errors can lead to financial loss, tax penalties, unsuitable asset allocation, or poor estate decisions, the lack of user warnings materially increases risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The quick-start phrases are generic financial requests like 'Build my investment portfolio' and 'When can I retire?', which are highly likely to overlap with normal user intent and trigger the skill without clear informed consent. In a financial-planning skill, accidental invocation can cause the agent to provide consequential investment, debt, tax, or retirement guidance in contexts where the user did not explicitly choose this capability or receive appropriate cautions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill is designed to collect and analyze net worth, debts, cash flow, insurance, retirement, and estate-planning details, but it does not prominently warn that these are highly sensitive data categories requiring careful handling. That omission increases the risk that users overshare personally identifiable and financial information without understanding the privacy implications, especially since the skill also encourages ongoing reviews and storage-like structured templates.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase "Help me build wealth" is broad and maps to a full assessment plus personalized action plan, which can collide with ordinary user requests and activate the skill unintentionally. In a finance skill, accidental invocation is more dangerous because it may solicit or process highly sensitive financial, tax, and estate data and provide influential financial guidance in contexts where the user did not explicitly opt in.

Content

No source excerpt is available for this finding.