playwright-ui-testing

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can be ingested into the agent’s LLM context via runtime-fetched page content from the user-supplied $URL (e.g., playwright-cli ... open "$URL" followed by run-code/snapshot/report generation that extracts DOM text like headings, labels, error messages, and link text).

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

• Potentially malicious external URL detected (high risk: 0.80). This skill's prerequisites auto-install and run Playwright and axe-core at runtime (e.g., "npm install -D @playwright/test", "npm install -D @axe-core/playwright", "npx playwright install ..."), which fetch and execute remote packages from the npm registry (https://registry.npmjs.org/) and download Playwright browser binaries (e.g., https://playwright.azureedge.net/) — these external endpoints are required runtime dependencies that result in executing remote code.