ClawHub
Back to skill

Security audit

KyberSwap Arbitrage

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent KyberSwap arbitrage guide, but it enables real on-chain trades without clear consent, irreversibility, or loss-risk controls.

Review this carefully before installing. It is not covert or obviously malicious, but it is designed around real cryptocurrency trades. Only use it in quote/simulation mode unless you intentionally approve each transaction, understand slippage and gas risks, validate token and recipient addresses, and are prepared for irreversible losses.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes direct guidance and code for executing on-chain token swaps but does not clearly warn that these actions can irreversibly move user funds, incur gas costs, and fail under slippage or market movement. In an agent setting, omission of an explicit transaction-risk warning is dangerous because it can normalize automated trade execution without ensuring informed user consent or confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.