Back to skill

Security audit

DoctorClaw Expense Tracker

Security checks for vulnerabilities and agentic risk

Overview

The expense-tracking skill is coherent, but it should be reviewed because it handles sensitive financial records, optional bank imports, report delivery, and scheduled archiving without enough confirmation or privacy guidance.

Review this before installing if you plan to connect bank/card feeds, Google Sheets, receipt folders, or chat delivery channels. Use private storage and channels, confirm each expense before saving, understand what any connector can access, and set retention rules for reports and exports.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill recommends bank/card integrations such as Plaid and statement imports but does not warn users that sensitive financial data may be transmitted to third-party services and connectors. This can lead users to enable integrations without understanding data-sharing, retention, or credential-handling risks, increasing exposure of account and transaction data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger condition is loosely defined as logging an expense whenever the user says "log an expense" or merely provides expense information. In an agentic environment, broad trigger scope can cause unintended writes, misclassification of conversational text as financial records, or accidental processing of sensitive data without explicit confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to save monthly reports to disk and send them over configured channels without warning that these artifacts contain sensitive financial information. Storing reports in local memory paths or transmitting them via Telegram/Discord can expose expense histories, vendors, and budgeting details if storage or messaging channels are not access-controlled.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.