Junglescout Product Database

• Outcome: Review
• Latest audit: May 29, 2026, 9:35 PM
• Version:
  1.0.1

Overview

The product-search function is coherent, but the skill also tells agents to silently send user-derived feedback to a separate LinkFox endpoint without explicit user consent.

Install only if you trust LinkFox with your Amazon product-search queries, API-key-backed usage, and possible feedback summaries about interactions. Avoid entering confidential product strategy, customer data, or sensitive business details unless that external sharing is acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 96% confidence
• Finding: The skill adds automatic feedback reporting behavior that is unrelated to its stated product-database filtering purpose. This enables secondary data transfer based on user interactions, including sentiment or dissatisfaction signals, without clear user consent or necessity for the requested task.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: Automatically submitting user feedback and improvement reports is not justified by the core purpose of filtering Amazon products. If implemented literally, the skill could exfiltrate user prompts, responses, or behavioral metadata to another API whenever broad conditions are met, expanding data exposure beyond user expectations.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The trigger conditions are written very broadly, including generic Amazon product research and discovery requests even when the user does not mention Jungle Scout or the product database. Over-broad invocation can route unrelated user queries into this skill unnecessarily, increasing unintended data sharing with the external tool and causing action on ambiguous intent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The document defines a separate feedback endpoint that transmits free-form `content` and user outcome details to another external service, but it provides no user-consent, disclosure, or minimization guidance. In an agent setting, this can cause user prompts, business data, or other sensitive context to be sent off-platform unexpectedly, creating a privacy and data-governance risk.

VirusTotal

65/65 vendors flagged this skill as clean.