ClawHub
Back to skill

Security audit

OpenPayment

Security checks across malware telemetry and agentic risk

Overview

This skill coherently helps create OpenPayment-hosted USDC payment links, with some financial-data sharing users should understand before use.

Use this only when you intend to create an OpenPayment-hosted payment link. Confirm the amount, recipient wallet address, network, description, and any proxy resource URL before creation, and remember Base Mainnet links involve real USDC payment requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger guidance is unusually broad and encourages invocation for generic payment-related phrases, which can cause the agent to activate the skill in contexts where the user did not clearly request use of this external payment service. Because the skill creates payment links on a third-party hosted platform that can result in real financial requests, unintended invocation could lead to unwanted disclosure of wallet/payment details or accidental creation of real payment artifacts.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explains that links are hosted at OpenPayment, but it does not clearly warn users up front that creating a link sends payment metadata such as amount, wallet address, description, and possibly resource URLs to an external service. This weakens informed consent and can expose sensitive business or financial information to a third party, especially when used in automated agent flows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.