ClawHub
Back to skill

Security audit

Off-chain x402 Payments

Security checks across malware telemetry and agentic risk

Overview

This payments skill is mostly coherent, but it includes automatic funding and payment examples without clear user consent or spending limits.

Review before installing. Use only dedicated low-balance test wallets until you understand the flow, pin and verify SDK dependencies, confirm the exact network and facilitator endpoint, and require explicit user approval and a spending cap before any deposit, asset update, or paid request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to call `manager.deposit(1000000)` and proceed with paid requests, but it does not provide a clear warning that this action spends real or test funds and may trigger automatic channel funding. In a payment skill, omitting an explicit spend-consent warning is dangerous because agents or operators may unknowingly authorize transfers, especially if adapted from testnet examples to production networks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.