ClawHub

Amazon Alexa For Shopping

Security checks across malware telemetry and agentic risk

Overview

The skill appears to provide the advertised Amazon shopping assistant, but it can send shopping prompts, Amazon page URLs, and broad feedback text to LinkFox services without clear user consent or data-minimization guidance.

Review before installing. Use this only if you are comfortable sending shopping questions, Amazon page URLs, and possible feedback text to LinkFox services. Do not include account credentials, payment details, order IDs, private business information, or sensitive URLs, and strip unnecessary tracking or query parameters before using page context.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation instructs users to send free-form prompts and optional page URLs to an external third-party endpoint, but it does not clearly warn that this may disclose user queries, shopping intent, or contextual page data outside the local agent environment. In a shopping assistant context, prompts and URLs can contain sensitive preferences, account-adjacent context, or links with tracking/query parameters, so omission of an explicit data-sharing notice creates a real privacy risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script forwards user-supplied prompts and any included page context to an external service at tool-gateway.linkfox.com without any explicit disclosure, consent flow, or redaction. In a shopping-assistant skill, users may include personal preferences, account-related details, or sensitive browsing context, creating a real privacy and data-handling risk even though the network call is the skill's intended function.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal