ClawHub
Back to skill

Security audit

Financial Loan Amortization Calculator

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed AgentPMT loan-calculation skill with an optional cloud CSV export that users should treat as sensitive financial data sharing.

Install only if you are comfortable sending loan and affordability inputs to AgentPMT. Leave store_schedule_file disabled unless you need a downloadable CSV, and avoid including unnecessary personal identifiers because exported schedules are stored in cloud storage and exposed through a signed URL until expiration.

SkillSpector

By NVIDIA
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
93% confidence
Finding
The skill supports `store_schedule_file: true`, which uploads amortization schedule data to cloud storage and returns a signed URL, but the documentation does not prominently warn users that enabling this feature transmits potentially sensitive financial data off-platform. Users may unknowingly expose loan balances, payment schedules, and related financial details to third-party storage, increasing privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The schema explicitly supports uploading amortization schedules as CSV files to cloud storage via `store_schedule_file`, but it does not warn that user-provided financial data may leave the local/system boundary. In a finance-oriented skill, amortization schedules can contain sensitive personal financial details, so silent export behavior increases privacy and data-handling risk if an agent enables it without clear user awareness or consent.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal