browser

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to navigate and interact with arbitrary public web pages (e.g., await page.goto('https://example.com')) and to extract/execute page content (page.$$eval, page.on('console')), so untrusted third-party page content can be read and used to drive subsequent actions.