puppeteer

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

• Third-party content exposure detected (high risk: 1.00). The skill's examples (e.g., takeScreenshot, scrapeData, submitForm) call page.goto(url) and page.evaluate to load and scrape arbitrary public URLs, meaning it ingests untrusted third-party web content from the open web which the agent reads and interprets.