Back to skill

Security audit

DoctorClaw Expense Tracker

Security checks across malware telemetry and agentic risk

Overview

This expense tracker is coherent, but it can handle sensitive financial data, so configure storage, integrations, and alerts carefully.

Install only if you are comfortable letting the agent handle business expense data. Prefer read-only or manual imports where possible, limit connected accounts and shared fields, secure receipt/report folders and sheets, and review what is sent to chat channels or accountants before enabling automatic delivery.

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
87% confidence
Finding
The skill explicitly encourages connecting bank/card integrations and sending reports via Telegram/Discord, but it does not warn that sensitive financial transaction data may be transmitted to third parties. This creates a real privacy and data-exposure risk because users may enable integrations or alerts without understanding that expense details, merchants, amounts, and budget status could leave their primary system.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill instructs the agent to save monthly reports to persistent storage under memory/expenses/YYYY-MM.md and export expense data, but it does not clearly warn users that sensitive financial records will be stored long-term. Persistent storage of expense history, notes, and possibly tax-related categorization increases confidentiality risk if the workspace, memory store, or backups are later accessed by unauthorized parties.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.