Back to skill

Security audit

AI-powered Automated Concentrated Liquidity Manager for Uniswap v4. Manage liquidity positions, auto-rebalance out-of-range positions, optimize LP fees dynamically, execute limit orders (stop-loss, take-profit), and monitor oracle signals — all from chat. Deployed on Ethereum Sepolia with verified contracts. Use this skill when users ask about DeFi liquidity provision, Uniswap v4 hooks, pool management, LP positions, impermanent loss, or automated market making.

Security checks for vulnerabilities and agentic risk

Overview

This Sepolia DeFi skill mostly matches its stated purpose, but it needs Review because it ships a default signing key and can make persistent blockchain approvals and transactions.

Install only if you are comfortable with Sepolia-only transaction scripts. Do not use a production wallet or a key with mainnet funds, rotate or replace the embedded demo key before relying on it, use your own restricted RPC endpoint, review allowances after adding liquidity, and prefer a version with pinned dependencies and explicit transaction confirmations.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/config.mjs:21
Finding

Hardcoded Ethereum Private Key Used as the Default Transaction Signer

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/config.mjs:21
Finding

Authenticated Alchemy RPC Credential Embedded in Source Code

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/package.json:1
Finding

Non-Reproducible Dependency Installation Without a Lockfile

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/add-liquidity.mjs:40
Finding

Excessive Token Allowances and Zero Slippage Protection in Liquidity Transactions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The file embeds a default private key and immediately derives an account and wallet client from it, which gives the skill transaction-signing capability even when no secret is intentionally provided by the operator. In a DeFi automation context, this is especially dangerous because anyone with the code can use the same key, and the agent may sign on-chain actions with a shared or exposed identity, leading to fund loss, abuse, or unauthorized transactions.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

Using a hardcoded private key as a silent fallback means the system can operate with a sensitive credential without operator awareness or explicit consent. In this skill, which manages Uniswap liquidity and trading-related actions, that increases the chance of unintended live transactions, shared-key compromise, and misleading assumptions about which wallet is actually controlling assets.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broad enough to activate on generic DeFi and AMM topics, not just narrowly scoped GhostBot operations. Because this skill includes transaction-capable scripts and wallet-related setup, over-triggering can route users into unnecessary blockchain actions or expose them to risky operational guidance when they only wanted general information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown provides concrete commands for adding liquidity and posting oracle signals, plus guidance for setting a private key, without prominent warnings about transaction signing, key handling, approval risk, or the danger of using a built-in demo wallet. Even on Sepolia, this normalizes unsafe secret management and can lead users to run signing actions they do not fully understand, a risk amplified if users adapt the workflow to mainnet or reuse sensitive keys.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest describes managing Uniswap v4 liquidity positions, rebalancing, fee optimization, and order/oracle-driven actions. In this file, if the user lacks enough tokens, the script directly calls token mint functions to create assets before adding liquidity, which is a materially different capability than managing existing LP capital.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The top comments present this as an add-liquidity utility, implying the action is limited to supplying liquidity. However, the code conditionally performs additional state-changing token mint operations, so the inline documentation understates and misrepresents what the script actually does.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The dependency version for viem is specified with a caret range, which allows newer minor and patch releases to be installed automatically. This can introduce supply-chain risk and non-reproducible builds if an upstream release is compromised or contains a breaking security regression, especially in a DeFi-related skill that may interact with blockchain transactions and funds.

Content

Scanner excerpt · scripts/package.json (reported line 6)May include surrounding context.

json
"type": "module",
  "private": true,
  "dependencies": {
    "viem": "^2.20.0"
  }
}

Static analysis

No suspicious patterns detected.