Amazon Reviews Api Skill

• Outcome: Pass
• Latest audit: Jul 10, 2026 · 5:21 AM UTC
• Version: 0.1.2

Overview

This is a straightforward BrowserAct integration for fetching Amazon reviews by ASIN, with expected third-party API use and no hidden persistence or destructive behavior.

Install this only if you intend to use BrowserAct for Amazon review extraction and are comfortable setting BROWSERACT_API_KEY. Confirm before running it on a product ASIN, and treat returned reviewer profile links or country data as personal or profile-related information that may have privacy or platform-policy implications.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill declares access to an environment variable and invokes a Python script that calls an external API, but it does not clearly declare or constrain those capabilities as permissions. This creates a transparency and governance gap: an agent may access secrets and perform networked data retrieval without an explicit permission boundary, making misuse or overreach harder to detect and review.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The description tells the agent to proactively apply the skill for a wide range of common research, analysis, and monitoring requests, which is overly broad for a networked data-extraction tool. That increases the chance of unintended activation, causing the agent to send user queries or target product identifiers to a third-party service without clear user intent or necessity.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill explicitly advertises collecting reviewer profiles and profile links for market research, but provides no privacy warning, minimization guidance, or limitation on handling personal data. Even if the information is publicly visible, aggregating profile identifiers at scale can facilitate profiling, scraping of individuals, or downstream privacy misuse beyond the user's reasonable expectations.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script sends both user-supplied ASIN data and a bearer API token to a third-party service, but provides no meaningful user-facing disclosure about what data is being transmitted or to whom. In an agent skill context, this is risky because the skill description encourages proactive use, increasing the chance data is sent off-platform without the user's informed consent.

External Transmission

Medium

• Category: Data Exfiltration

Content

# 1. Start Task
    print(f"Start Task", flush=True)
    try:
        res = requests.post(f"{API_BASE_URL}/run-task-by-template", json=payload, headers=headers).json()
    except Exception as e:
        print(f"Error: Connection to API failed - {e}", flush=True)
        return None

• Confidence: 93% confidence
• Finding: requests.post(f"{API_BASE_URL}/run-task-by-template", json=

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.