Google Maps Reviews Scraper Apify

• Outcome: Pass
• Latest audit: Jun 1, 2026, 3:43 PM
• Version:
  1.0.0

Overview

This is a coherent Apify-based Google Maps reviews scraping skill, with privacy-sensitive reviewer profile collection that users should intentionally control.

Install only if you are comfortable sending Google Maps place identifiers and resulting review data to Apify. Use a scoped Apify token, set a budget limit, and set personalData=false unless reviewer names, profile URLs, photos, or related profile fields are truly needed and lawful for your use case.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill declares use of environment variables, local file access, and network access to run an external Apify actor, but it does not expose an explicit permissions model or user-facing capability declaration. This reduces transparency and can lead to overbroad execution in agent environments, especially because the skill reads secrets from APIFY_TOKEN and sends user-supplied inputs to a third-party service.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly supports collection of reviewer profile fields and a personalData option, but it does not provide a clear privacy warning, lawful-use guidance, or data minimization defaults. This can cause users or downstream agents to collect personally identifiable or profile-linked data without understanding privacy, compliance, or terms-of-service implications.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The manifest explicitly instructs the agent to run an external Apify actor using APIFY_TOKEN, but provides no user-facing disclosure, consent step, or guidance on credential handling. This creates a real risk that the agent will send user-derived data to a third-party service and use stored credentials opaquely, which can lead to unintended external data sharing or misuse of privileged tokens.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The contract explicitly supports collection of public reviewer profile fields via the `personalData` flag, but it does not include any privacy notice, lawful-use guidance, minimization requirement, or warning about handling personal data. Even if the data is publicly exposed by Google, aggregating and exporting reviewer identifiers, profile URLs, names, photos, and review counts can create privacy and compliance risk for downstream users if they collect or retain it without adequate notice and controls.

VirusTotal

65/65 vendors flagged this skill as clean.