Smart Expense Tracker

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 2:38 AM UTC
• Version: 1.1.0

Overview

This is a local personal expense-tracking skill that stores and reports finance records on disk, with no evidence of hidden network access, persistence, or exfiltration.

Install only if a Chinese/CNY-oriented local expense tracker fits your use case. Back up ~/.openclaw/workspace/data/expenses/expenses.json before deleting records or making large edits, because deletion is permanent and there is no built-in undo.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill documents Python scripts that read and write local files and are invoked via shell commands, but it does not declare any explicit tool scope or permissions. This creates a capability/expectation gap: an agent or user may run file and shell operations without clear restriction, increasing the chance of unintended filesystem access or misuse if the implementation is broader than the documentation suggests.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill advertises a delete command for records without any warning, confirmation prompt, backup advice, or recovery guidance. In a finance-tracking context, deleting entries can silently destroy accounting history and undermine report integrity, especially if an agent executes the command from ambiguous user intent or with an incorrect ID.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: This JSON hard-codes category names and most matching keywords in Chinese while also setting locale-like defaults such as CNY currency. Because the file provides no natural-language indication of user opt-in or that the skill is intentionally limited to a Chinese-speaking or China-specific context, it appears to impose a language/locale choice unilaterally.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: This Python skill is entirely described and operated in Chinese, including the module docstring and all CLI help/error messages, with no indication that the language choice is optional or tied to a region-specific requirement. Under the policy rule for language/locale constraints, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: This code file contains natural-language descriptions and CLI help text that assume Chinese as the only supported language. Under the language/locale policy, forcing a specific language without user opt-in or a documented regional justification is a policy concern.

Static analysis

No suspicious patterns detected.