ClawHub
Back to skill

Security audit

Local Budget

Security checks across malware telemetry and agentic risk

Overview

This is a local budgeting helper that reads user-provided financial CSVs and writes local JSON or markdown reports, with privacy caveats but no evidence of hidden data sharing or destructive behavior.

Install only if you are comfortable processing bank or credit-card exports with local scripts and with the agent reviewing transaction data for categorization. Keep CSVs and generated JSON/markdown reports in a private local folder, avoid synced or shared Obsidian vaults unless intended, and review low-confidence categories before relying on the report.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to create JSON and markdown output files and explicitly suggests writing reports into user-selected locations such as an Obsidian vault, but it declares no permissions. That mismatch matters because financial CSVs contain sensitive data, and undeclared write behavior reduces transparency and may lead to accidental creation of sensitive artifacts in unsafe locations.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger phrases are very broad and cover common finance-related language such as budget, spending, transactions, and monthly expenses. That increases the chance of unsolicited activation in ordinary conversations, which is risky here because the skill handles highly sensitive financial files and may prompt file processing or report generation when the user did not intend to invoke it.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill tells the agent to parse bank and credit-card exports and generate JSON/markdown reports, including saving directly into an Obsidian vault, but it does not warn that these outputs can contain account activity, merchant names, dates, and spending patterns. In context, this is more dangerous because the data is inherently sensitive financial information, and writing derivative files expands the exposure surface beyond the original export.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal