install-playwright-mcp
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
@playwright/mcppackage from the official NPM registry vianpxduring installation. - [COMMAND_EXECUTION]: Instructs the agent to run the
claude mcp addcommand to register the browser automation server within the Claude Code environment. - [PROMPT_INJECTION]: The skill facilitates the processing of untrusted data from external websites, creating a surface for indirect prompt injection.
- Ingestion points: Data from external URLs enters the agent context via browser tools like
browser_navigateandbrowser_snapshot. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the installation instructions.
- Capability inventory: The resulting tools allow the agent to click, type, navigate, and extract structured data within a browser environment.
- Sanitization: No automated sanitization or filtering is performed on the content retrieved from external web pages.
Audit Metadata