testing-specialist

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

• Third-party content exposure detected (high risk: 0.90). The skill includes explicit, required runtime instructions to fetch and scrape arbitrary public websites (e.g., references/domains/javascript-testing/puppeteer.md shows scrapeWebsite/processMultipleUrls that call page.goto() on arbitrary URLs) and the api-tester subskill declares a WebFetch tool (references/domains/testing/api-tester.md), so the agent will ingest untrusted third‑party web content and act on it as part of its workflow.