registry / snapmcp / 2.3.2

snapmcp@2.3.2

All-in-one MCP server for visual captures: terminal, code, browser, markdown, diffs, HTML, and PDF — via Playwright

AI Security Review

scanned 1d ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

One or more suspicious static signals were detected.

Trigger

User runs the setup/init command; Chromium download runs at npm postinstall.

Impact

Can alter detected AI-client configuration to launch snapmcp through npx; no covert exfiltration or foreign-agent mutation during install was confirmed.

Mechanism

MCP client config registration plus Playwright browser installation.

Rationale

This is an explicit-user-command AI-agent configuration mutation with a non-interactive default-yes path, so it warrants a warning. No concrete malicious chain, credential theft, covert payload, or unconsented install-time AI-client mutation was found.

Evidence

package.jsonscripts/postinstall.tsscripts/setup.tsdist/setup-shared.jsdist/register.js~/.config/opencode/opencode.json~/.config/Claude/claude_desktop_config.json~/.config/windsurf/settings.json~/.config/Cursor/User/settings.json

Decision evidence

public snapshot

snapmcp@2.3.2

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code