ClawHub
Back to skill

Security audit

流动性管理工具

Security checks for vulnerabilities and agentic risk

Overview

This skill is for Uniswap liquidity management, but its activation scope is inconsistent and it describes fund-moving actions without clear user confirmation requirements.

Review this carefully before installing. It may be useful for Uniswap liquidity lookups, but do not let it execute wallet, RPC, add-liquidity, remove-liquidity, modify, delete, save, or export actions unless you have checked the exact pool, chain, token amounts, fee tier, gas cost, and destination yourself and explicitly approve each step.

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)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The trigger-condition section says the skill should be used for design, UI, poster, and brand-visual tasks, which directly contradicts the documented purpose of Uniswap liquidity management. In an agentic environment, this can cause the skill to be invoked in unrelated contexts, increasing the chance of inappropriate tool use and confusing users about the skill’s actual capabilities.

Vague Triggers

High
Confidence
97% confidence
Finding
The trigger description is unrelated to the skill domain and overly broad, making it likely that an agent may select this skill for arbitrary requests outside DeFi. Because the skill is permitted to use exec/write and describes operational workflows, overbroad triggering raises the risk of unintended command execution or user confusion in contexts where the skill should never run.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description says to use the skill whenever the user needs liquidity-mgr-tool-free-related functionality, which is circular and too vague to safely gate invocation. This weak scoping can cause accidental activation whenever the tool name or adjacent wording appears, reducing assurance that the skill is chosen only for appropriate, user-intended tasks.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill advertises add/remove/save/export-style operations for liquidity positions and result handling, but it does not require explicit confirmation before actions that may move funds, alter positions, or persist data. In the context of DeFi, even a single unintended execution can cause irreversible on-chain transactions, financial loss, or accidental disclosure/storage of sensitive outputs.

Static analysis

No suspicious patterns detected.