Back to skill

Security audit

Manage YNAB budgets, accounts, categories, and transactions.

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward YNAB budgeting helper, but it can change live financial data if the user runs write or delete commands.

Install only if you trust the third-party ynab-cli package and are comfortable giving it a YNAB API key. Treat the key like a password, avoid exposing it in logs or screenshots, and require explicit confirmation before any create, update, delete, budget-allocation, or raw API command against live budget data.

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
88% confidence
Finding
The skill explicitly documents state-changing and destructive operations such as transaction creation, update, deletion, budget allocation changes, and raw POST requests without any warning, confirmation guidance, or backup/scope caution. In a financial-management context, this increases the chance that an agent or user will perform irreversible or unintended modifications to live budget data, causing data integrity issues or financial confusion.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The authentication section instructs users to obtain and use a YNAB API key but provides no guidance on secure handling, storage, redaction, or avoiding exposure in logs and shell history. Because the key grants access to sensitive budgeting data and write operations, poor credential hygiene could lead to unauthorized access or unintended disclosure of financial information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.