Back to skill

Security audit

Expense Tracker Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local expense tracker, but users should understand it stores sensitive spending records locally and can export them to CSV.

Install only if you are comfortable storing expense details in local Clawd memory. Avoid entering information you would not want retained, and treat any CSV exports as sensitive files that may need secure storage or deletion.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (5)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
87% confidence
Finding

The trigger "log expense" overlaps with the built-in command namespace around "log," creating a shadowing risk where user intent may be misrouted between core functionality and the skill. In practice, this can cause accidental invocation, confusion, or unintended handling of sensitive finance-related input by the wrong component.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase "track spending" is broad enough to match ordinary budgeting or finance questions that may not be intended to invoke this specific skill. In a skill that persists financial data, accidental activation can cause unintended recording, querying, or exposure of sensitive spending information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "what did I spend" is ambiguous and resembles a normal user question rather than an intentional skill invocation. Because the skill handles persistent financial records, ambiguous triggering increases the risk of accidental access to sensitive summaries or unintended data operations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill mentions that expense data persists in local memory but does not clearly warn users up front that sensitive financial information will be stored. Users may disclose transactions, merchants, and budgeting details without informed consent, creating privacy and retention risks on shared or compromised machines.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Advertising CSV export without warning that financial records will be written to disk can lead users to create unprotected files containing sensitive spending history. Such files may be accessible to other local users, backups, sync services, or malware, increasing confidentiality risk beyond in-memory storage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.