ClawHub
Back to skill

Security audit

Agentic Commerce Relay

Security checks for vulnerabilities and agentic risk

Overview

The skill is a clear USDC cross-chain relay helper, but it should be used only as a real-money transaction tool that handles a wallet private key.

Install only if you understand that this is for signing real blockchain transactions. Use a dedicated low-balance wallet, verify the actual relay script before running it, start with testnets or minimal amounts, and keep private keys out of logs, command history, and committed files.

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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation tells users to run a relay that performs live cross-chain settlement but does not clearly warn that it will sign and submit real on-chain transactions, including a USDC burn on the source chain. In an agent skill context, this omission is dangerous because operators may treat the command as a harmless utility invocation and unintentionally authorize irreversible asset movement with their private key.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documentation instructs users to provide a raw PRIVATE_KEY environment variable without any warning about secret exposure risks such as shell history, process inspection, CI logs, and accidental commits. Because this skill directly handles real-value settlement, poor credential hygiene can lead to wallet compromise and theft of funds beyond the intended relay transaction.

Static analysis

No suspicious patterns detected.