ClawHub
Back to skill

Security audit

DeFi Stablecoin Yield Scanner

Security checks across malware telemetry and agentic risk

Overview

This skill only fetches public DeFiLlama yield data and prints filtered results, with no wallet, credential, or fund-moving behavior.

Installers should treat results as a shortlist, not financial advice: the skill is read-only, but APY data can be stale or incentive-driven, so verify pool contracts, audits, and reward composition before depositing funds.

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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.