Back to skill

Security audit

支出追踪器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple expense-tracking skill with disclosed local JSON storage and no executable code, network behavior, or hidden privileges.

Install this only if you are comfortable with expense and budget details being kept in local JSON files named expenses.json and budget.json. On shared machines, review or delete those files when needed, and be aware the skill may activate on broad Chinese finance phrases.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The description, headings, features, triggers, and examples are all presented in Chinese, and the file does not indicate that this is an optional language mode or a region-specific skill. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger list includes generic phrases such as “记录支出”, “设置预算”, “本月支出”, and “预算多少”, which are common finance-related utterances that could arise in normal conversation. The description does not provide activation boundaries, exclusions, or negative examples to clarify when the skill should or should not activate.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly stores expense and budget data persistently in local files, but it does not disclose that user financial information will be written to disk. Because expense records can reveal sensitive behavioral and financial details, undisclosed persistence creates privacy and consent risks, especially on shared or unmanaged systems.

Static analysis

No suspicious patterns detected.