ClawHub
Back to skill

Security audit

Expense Tracker Pro

Security checks across malware telemetry and agentic risk

Overview

Expense Tracker Pro is a local, documentation-only expense tracking skill with disclosed local persistence and no evidence of hidden commands, network access, or malicious behavior.

Safe to install based on the provided artifacts. Before using it, remember that expense and budget details may remain in local Clawd memory, and CSV export may create local files; avoid entering highly sensitive financial details unless you are comfortable managing them locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrase "track spending" is broad enough to match ordinary user requests about finances, which can cause the skill to activate unexpectedly. In a skill that persists local financial data, accidental invocation can lead to unintended logging, retrieval, or export-related actions based on ambiguous user input.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger "what did I spend" is a very general question pattern that overlaps with normal conversational queries, so the skill may intercept requests without clear user intent to invoke this specific tool. Because the skill handles sensitive financial history stored in local memory, mistaken activation increases the risk of exposing or operating on personal expense data in the wrong context.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
84% confidence
Finding
The trigger "log expense" collides with the built-in concept of "log," creating a shadow-command risk where the skill may override or interfere with expected platform behavior. Even without malicious intent, command ambiguity can redirect user actions into this skill, causing unintended recording of financial data or confusing command resolution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.