Security audit

Revenue Tracker (Tianyi)

Security checks for vulnerabilities and agentic risk

Overview

This is a local revenue-tracking skill with some broad automation language, but the inspected package shows no hidden code, credentials, external payloads, or destructive behavior.

Before installing, confirm where OpenClaw model calls are processed if you plan to enter private financial data, and be aware that the published artifact appears to reference scripts that are not included.

A.I.G

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

SkillSpector

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: All user-facing instructions, headings, and usage guidance in the README are presented only in Chinese. This can constitute a language policy violation because the skill effectively forces a specific language without giving the user an opt-in choice or documenting a justified region-specific constraint.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The title, headings, examples, triggers, and output templates are all presented in Chinese, and the sample outputs implicitly enforce Chinese responses. There is no indication that users may choose another language or that the locale restriction is required for a region-specific compliance reason.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger conditions are broad enough that the skill could activate on loosely related events such as any income/expense change, user pricing requests, or scheduled report generation without clear scoping, confirmation boundaries, or precise event definitions. In a finance-related skill, unintended activation can lead to accidental record changes, misleading reports, or unnecessary model invocations, especially because the document also describes autonomous model use and integration with another skill.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: This markdown file instructs users to run commands that record income, record expenses, and generate reports, and later documents a file structure containing logs and reports. The description does not warn that these operations will create or update local financial data files, which is a user-data-affecting behavior covered by markdown warning requirements.

Static analysis

No suspicious patterns detected.