ClawHub
Back to skill

Security audit

Graph Aave MCP

Security checks across malware telemetry and agentic risk

Overview

This skill is a purpose-aligned Aave data-query MCP server with expected network/API-key use and no evidence of hidden wallet access, transactions, exfiltration, or destructive behavior.

Install only if you are comfortable running a community npm MCP server and sending Aave-related queries, wallet addresses, and related parameters to The Graph and Aave infrastructure. Use a separate or least-privilege Graph API key where possible, and do not provide wallet private keys or seed phrases because this skill does not need them.

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

Low
Confidence
86% confidence
Finding
The skill explicitly requires a third-party GRAPH_API_KEY and encourages API-backed use, but it does not disclose that user queries and related parameters may be sent to external Graph/Aave services. This is a real transparency and privacy issue because users may provide wallet addresses, positions, or investigative data without understanding that those inputs leave the local environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.