playwright-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill autonomously visits and interacts with arbitrary web pages (e.g., SKILL.md workflow and example scripts call page.goto on user-provided or public URLs, the "Check for Broken Links" example and helpers.extractTexts/extractTableData/handleCookieBanner actively fetch and parse third-party page content), so untrusted public web content can be ingested and influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). run.js invokes npm/npx to install and run Playwright at runtime, which will fetch and execute remote package code from the npm registry (e.g. https://registry.npmjs.org/playwright/-/playwright-1.58.1.tgz), and the skill depends on that external package to run.