Security audit

Zhua Economy

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it asks an agent to handle pricing, transactions, and revenue distribution with broad autonomy and little scoping or user-control guidance.

Review this skill carefully before installing. It appears to be a placeholder economy-planning skill rather than a working implementation, and its financial workflows should not be used for real transactions or revenue allocation unless you add explicit authorization, validation, dry-run behavior, audit logging, and clear limits on what the agent may change.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The description claims a substantive economy-system skill with capabilities around monetization, pricing, profit allocation, and autonomy. However, the actual code chunk is a minimal example script whose only behavior is printing a message indicating it is an example for zhua-economy. It does not access resources, implement business logic, or perform any of the declared functions. This is a clear description-to-behavior mismatch because the primary declared purpose is not represented by the code at all.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The manifest description says to use the skill when 爪爪 needs to build an economic system, monetize skills, or achieve economic autonomy, but it does not define concrete trigger phrases, scope boundaries, or exclusion conditions. These concepts are broad enough that the skill could be invoked in many loosely related conversations about money, pricing, or autonomy.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The workflow includes commands for recording transactions, calculating revenue, and distributing revenue without any warning, approval gate, or validation guidance. In an agent context, this creates a real risk of unauthorized or mistaken modification of financial records or allocations if the commands are executed automatically or by an over-trusting operator.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The file presents key operational guidance primarily in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can amount to a language-policy issue when a specific language is effectively imposed without opt-in or justification.

Static analysis

No suspicious patterns detected.