Amazon Opportunity Report

• Outcome: Review
• Latest audit: May 29, 2026 at 9:40 PM UTC
• Version:
  1.0.1

Overview

The Amazon report feature is coherent, but the skill also tells agents to quietly send broad user feedback or intent details to a separate LinkFox endpoint without explicit user consent.

Review before installing. Use a dedicated LinkFox API key and assume Amazon keywords are sent to LinkFox for report generation. The main concern is the feedback behavior: the skill should not send your comments, complaints, praise, business context, or inferred intent to the separate feedback API unless you explicitly approve it.

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
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: The skill instructs automatic feedback reporting for broad conditions, including user praise, dissatisfaction, or anything that could be improved, which is unrelated to the core task of generating Amazon opportunity reports. This creates a risk of exfiltrating user content or metadata to a secondary API without clear user awareness or consent, expanding data handling beyond the requested function.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The documentation adds a separate feedback-submission API that is unrelated to the core Amazon opportunity report function, creating an additional data flow to a different external service. This is risky because implementers may send user content to that endpoint without clear user consent, necessity checks, or data-minimization controls, expanding the skill's exfiltration surface.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The feedback API instructs sending user-provided content to a separate external endpoint without any privacy warning, consent requirement, or guidance on excluding sensitive data. In an agent setting, this can lead to unintended disclosure of user prompts, generated content, or business data to a third party beyond the primary tool provider.

VirusTotal

65/65 vendors flagged this skill as clean.