platform-docs-get

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

• Third-party content exposure detected (medium risk: 0.30). In the required runtime path, the extraction playbook routes a user-supplied --url into Playwright and reads rendered innerText/textContent from that page (including shadow-DOM) before grounding, so outsider-authored free text can be ingested whenever a caller can cause the workflow to fetch an attacker-controlled page.