ClawHub
Back to skill

Security audit

Clawpay

Security checks across malware telemetry and agentic risk

Overview

This payment skill is purpose-related, but it asks an agent to handle a wallet private key and perform real blockchain transfers without enough safety boundaries.

Review carefully before installing. Use only a dedicated wallet with minimal funds, never paste or hardcode a valuable private key, verify every recipient and amount, and avoid using this unless you trust clawpay.dev and understand what signed messages and on-chain transfers authorize.

SkillSpector

By NVIDIA
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

High
Confidence
97% confidence
Finding
The skill explicitly tells users to supply a wallet private key and run a script that performs a live on-chain token transfer, but it provides no safety guidance about irreversible transactions, key exfiltration risk, or the trust assumptions around the remote service. In an agent-skill context this is especially dangerous because users may copy-paste secrets into automation workflows and authorize real fund movement with minimal review.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The example sends the user's wallet address and a reusable signed message to clawpay.dev endpoints without clearly warning that this shares wallet-linked metadata with a third-party service. Although not a private key leak, the signature and address can still create account linkage, service-side tracking, and misuse risk if users do not understand what authorization or identity proof they are providing.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.