playwright-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md: "auto-detect running dev servers (or ask for URL if testing external site)") plus run.js and the provided examples (page.goto to arbitrary URLs in SKILL.md/API_REFERENCE.md and helpers like extractTexts, extractTableData and the "check for broken links" script in lib/helpers.js) show the agent will fetch and interpret untrusted public web pages and follow links, allowing third‑party content to materially 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 install / npx playwright at runtime which will fetch and install Playwright from the npm registry (e.g. https://registry.npmjs.org/playwright/-/playwright-1.59.1.tgz), causing remote code to be downloaded and executed as a required dependency.