browsing-with-playwright

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill navigates arbitrary web pages and extracts content via Playwright MCP tools, which can expose the agent to untrusted external text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs execution of npx @playwright/mcp@latest fetched from npm at runtime, which constitutes an unpinned public registry package reference rather than a direct repository URL or verified strong dependency source.