ClawHub
Back to skill

Security audit

DeFi Research

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent paid DeFi lookup helper, but it asks wallet-enabled agents to send USDC payments without enough safeguards for irreversible transfers.

Review before installing. Use this only with manual approval for every payment, a low-balance dedicated wallet, verified Base/USDC recipient details, and scoped API keys. Do not allow autonomous spending or broad wallet permissions.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users or agents to send irreversible USDC payments directly to a blockchain address without any prominent warning about irreversibility, address verification, network correctness, or payment-finality risks. In the context of an autonomous DeFi/flash-loan-oriented skill, this is more dangerous because agents may act quickly or automatically, increasing the chance of mispayment, spoofed payment flows, or unrecoverable fund loss.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.