ClawHub
Back to skill

Security audit

Personal Finance Mastery

Security checks for vulnerabilities and agentic risk

Overview

This is a finance-planning methodology skill with sensitive-data handling considerations, but no hidden execution, exfiltration, persistence, or unsafe install behavior was found.

Use this skill with redacted or summarized financial data where possible. Do not paste bank credentials, full account numbers, SSNs, tax IDs, or wallet recovery phrases into an agent, and keep any generated finance files in a location you control and protect.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The README promotes 'daily transaction categorization' and other automated personal-finance workflows, which implies handling highly sensitive financial data, but it provides no privacy, security, or data-sensitivity warning. In a personal-finance skill, this omission can lead users to expose bank transactions, account balances, tax details, or other confidential information to agents or integrations without understanding the risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill proposes continuous automation over highly sensitive financial data such as transactions, balances, net worth, insurance, and estate records, but provides no privacy notice, consent model, retention limits, or guidance on secure handling. In a finance-focused skill, this omission is materially risky because users may supply bank, tax, and account data under the assumption it will be safely processed, creating exposure through overcollection, unintended storage, or disclosure.

Static analysis

No suspicious patterns detected.