ClawHub
Back to skill

Security audit

Arb Spread

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped paid crypto trading-signal fetch, but it uses an EVM private key to automatically authorize per-call USDC payments.

Review this before installing if the wallet contains meaningful funds. Use a dedicated low-balance wallet, understand that each invocation may charge USDC on Base mainnet, and require explicit approval before any agent calls the endpoint.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Confidence
93% confidence
Finding
The skill triggers an x402-authenticated request that can automatically authorize paid access using the user's EVM private key and on-chain USDC balance, but the warning is not surfaced prominently as a primary risk. This creates a meaningful consent and financial-spend risk: an agent or user may invoke the endpoint assuming it is a normal unauthenticated data fetch, resulting in unintended charges.

Static analysis

No suspicious patterns detected.