ScrapingBee Fetch

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward ScrapingBee-based page fetcher, with some privacy considerations because requested URLs are sent to a third-party service.

Install only if you are comfortable using ScrapingBee as a third-party processor for the URLs you fetch. Keep the API key out of source control, and do not use this on private/internal URLs, URLs containing tokens, or sensitive research targets unless that data flow is approved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
79% confidence
Finding
The documented behavior does not fully match the actual capability set, especially around proxy/geolocation options and special-case handling for Google. This mismatch can mislead users about where requests are routed, what content is accessed, and how data is processed, which increases the risk of policy bypass, unexpected data transfer, or misuse in more restricted environments.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill sends user-supplied target URLs to ScrapingBee along with the API key, which means browsing targets and associated metadata are disclosed to a third-party processor. In this skill context, that is expected for functionality, but the lack of explicit warning or consent can expose sensitive internal URLs, tokens embedded in URLs, or confidential research targets.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal