Is zoharbabin/google-researcher-mcp safe to install?

zoharbabin/google-researcher-mcp was flagged as CRITICAL RISK (risk score 170) with 19 findings detected across 139 files. Review the findings before installing.

What security issues were found in zoharbabin/google-researcher-mcp?

Sigil detected 19 findings in zoharbabin/google-researcher-mcp, including patterns related to provenance, install_hooks, code_patterns, credentials. See the full scan report for details.

Scans/github/zoharbabin/google-researcher-mcp

zoharbabin/google-researcher-mcp

github

Summary

zoharbabin/google-researcher-mcp v2026-04-10 was classified as CRITICAL RISK with a risk score of 170. Sigil detected 19 findings across 139 files, covering phases including provenance, install hooks, code patterns, credential access. Review the findings below before installing this package.

Package description: This is a Model Context Protocol (MCP) server that enables AI assistants like Claude, GPT, and other LLMs to: Search the web via Google (general, images, news) Read any webpage including JavaScrip...

CRITICAL RISK(170)

v2026-04-10

24 April 2026, 05:33 UTC

by Sigil Bot

Risk Score

170

Findings

Files Scanned

139

Provenance

Registry

https://github.com/zoharbabin/google-researcher-mcp

Repository

https://github.com/zoharbabin/google-researcher-mcp

Scanned From

https://github.com/zoharbabin/google-researcher-mcp.git

Findings by Phase

•

Phase Ordering

Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.

install-npm-postinstall

CRITICAL

npm lifecycle script — runs automatically on install

repo/package.json:65

    "prepare": "npm run build",
    "postinstall": "npx playwright install chromium 2>/dev/null || echo 'Note: Playwright browser install skipped (run npx playwright install chromium manually if scraping JS-rendered pages)'",
    "prepublishOnly": "npm run build && npm test",

Why was this flagged?

npm lifecycle scripts like postinstall run automatically during package installation with no user interaction required. This is the #1 attack vector for malicious npm packages — attackers embed data theft or backdoor installation in these hooks. Rated CRITICAL because code executes before the developer can review it.

Badge

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/github/zoharbabin/google-researcher-mcp)](https://sigilsec.ai/scans/9CA22EF7-A7A8-46DD-A707-3D8839E5E696)

HTML

<a href="https://sigilsec.ai/scans/9CA22EF7-A7A8-46DD-A707-3D8839E5E696"><img src="https://sigilsec.ai/badge/github/zoharbabin/google-researcher-mcp" alt="Sigil Scan"></a>

Run This Scan Yourself