ClawHub
Back to skill

Security audit

AgentFuel API

Security checks across malware telemetry and agentic risk

Overview

This is a coherent instruction-only API integration for AgentFuel, but users should treat the funded API key and crypto payment steps carefully.

Install only if you trust AgentFuel as a payment-backed API gateway. Treat AGENTFUEL_KEY like a payment credential, prefer Authorization headers over URLs containing ?key=, avoid sending sensitive prompts unless you trust the gateway and upstream providers, and manually verify all invoice and transfer details before moving credits or funds.

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
98% confidence
Finding
The skill explicitly recommends passing the API key in the URL query string, which is commonly logged by browsers, proxies, analytics systems, server access logs, and agent tooling. This can expose the AgentFuel credential to unintended parties, enabling unauthorized use of the account and consumption or transfer of credits.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal