ClawHub

Teller MCP – Borrow USDC & Altcoins

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Teller MCP server, but users should review any generated borrow or repay transaction before signing it.

Install only if you intend to use Teller lending tools through an MCP server. Use the default Teller endpoint or another endpoint you trust, avoid sharing wallet addresses unnecessarily, and independently verify destination, chain, amounts, approvals, and calldata before signing any generated borrow or repayment transaction.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs users to install and run a bundled MCP server that explicitly uses network access and environment variables, but the skill declares no permissions to reflect those capabilities. This creates a transparency and policy-enforcement gap: users or orchestrators may treat the skill as lower risk than it is, while the server can still make outbound requests to Teller endpoints and consume environment-based configuration.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The README explicitly advertises per-wallet data retrieval and generation of encoded on-chain borrow/repay transactions, but it does not warn users that wallet addresses are sensitive financial metadata or that generated transactions can move funds and should be independently reviewed before signing. In an agent/MCP context, this omission increases the chance that operators treat the tool as low-risk infrastructure and allow automated use without appropriate consent, transaction review, or privacy controls.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal