researching-with-playwright

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

• Third-party content exposure detected (high risk: 0.90). This skill clearly navigates and scrapes arbitrary public web pages (e.g., scripts/basic-scraper.js and scripts/extract-documentation.js call page.goto(url) and extract headings, code blocks, links, and other page content, and SKILL.md contains multiple scraping patterns that ingest arbitrary URLs), exposing the agent to untrusted third‑party content that could carry indirect prompt injections.