@agimon-ai/po-browse-tool@0.30.14-alpha.1
MCP server for browser automation using Playwright with profile management, page registry, and multi-browser support
AI Security Review
scanned 21d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the runtime behavior inspected is aligned with browser automation requested through the package. The scanner’s process and network flags map to browser setup and configured automation; the extension’s telemetry is disabled by default and gated by configuration.
Decision evidence
public snapshot- The manifest points to browser runtime bundles and defines no npm install lifecycle hook.
- The runtime operates on bound browser pages and dispatches requested browser actions such as clicking caller-selected elements.
- HTTP routes accept a requested tool and arguments, then dispatch them through the server’s tool registry.
- Playwright web-server commands and browser startup diagnostics support the package’s automation function; no unrelated outbound command-output transfer was identified.
- Extension telemetry starts disabled and sends traces only when enabled and an endpoint is configured.
- Chrome metadata is fetched from the Chrome for Testing feed as part of browser setup.
Source & flagged code
6 flaggedPackage source references child process execution.
dist/dockerChromeForTesting-BpNc3_AC.mjsView on unpkg · L1A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/dockerChromeForTesting-BpNc3_AC.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @agimon-ai/po-browse-tool@0.30.14-alpha.1.
See all versions of @agimon-ai/po-browse-tool for other recorded verdicts.
- Review the evidence and your use of @agimon-ai/po-browse-tool@0.30.14-alpha.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.