ClawHub

Financial Categorizer

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local finance CSV-to-SQLite tool, with expected database mutation commands but no evidence of hidden network access, credential use, or deception.

Install only if you are comfortable with a local CLI that can modify your finance database. Keep backups of the SQLite database before running delete, cleanup, auto-link, or bulk recategorization commands, and prefer dry-run options where available.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The documentation exposes destructive commands such as delete-account, delete-category, remove-rule, unlink, and db-cleanup without visible warnings, confirmation expectations, or backup guidance. In a financial data management context, users may run these commands on a live SQLite database and accidentally delete records or relationships, causing integrity loss and potentially corrupting analytical results.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The delete-account command performs an irreversible destructive action immediately after parsing arguments, with no confirmation prompt, safety interlock, or preview of downstream effects. In a financial data management tool, mistaken invocation can permanently remove account data or related state, causing integrity loss and potential operational disruption.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The delete-category command can remove category records and optionally reassign related data without a clear pre-action confirmation, increasing the chance of accidental destructive changes. Given that categories drive transaction classification and reporting, an unintended deletion can corrupt analytics, break rule organization, or cause hard-to-reverse data integrity issues.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The cleanup command can delete orphaned database records when run without '--dry-run', but it does so without an upfront warning or confirmation barrier. In a database-backed finance tool, accidental cleanup may remove records unexpectedly and alter calculated amounts, creating integrity and auditability problems even if the intent is maintenance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal