ClawHub
Back to skill

Security audit

流动性管理工具专业版

Security checks for vulnerabilities and agentic risk

Overview

The skill is a DeFi liquidity-management guide, but it combines broad execution/write authority with automated financial actions and a mismatched trigger that could invoke it outside its stated purpose.

Review this skill carefully before installing. It may be useful for DeFi liquidity management, but only use it with tightly scoped prompts, test or simulation mode first, explicit transaction review, conservative wallet permissions, and no unrestricted API keys or signer access. The trigger text should be corrected so it cannot activate for unrelated DevOps or monitoring tasks.

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 (3)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The trigger condition says the skill should be used for system monitoring, log analysis, alerting, and deployment management, which does not match a DeFi liquidity-management skill. This mismatch can cause the agent to invoke the skill in unrelated operational contexts, increasing the chance of inappropriate execution paths and unsafe tool use.

Vague Triggers

High
Confidence
96% confidence
Finding
The invocation criteria are broad and domain-mismatched, making it more likely the agent will select this skill when a user asks about generic monitoring or operations tasks. Because the skill exposes read/exec/write tools and discusses automated financial actions, unintended invocation could lead to unsafe commands, config changes, or financial workflow execution in the wrong context.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill describes automatic rebalancing, limit-order-like execution, and position migration but does not clearly warn that these may result in live on-chain financial transactions with loss, slippage, gas, and market risk. In a financial automation context, lack of an explicit execution-risk warning can mislead users into enabling actions that move funds or alter exposure without informed consent.

Static analysis

No suspicious patterns detected.