browsh

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly launches a text-based web browser and opens arbitrary web pages (see SKILL.md: "Open a specific URL: browsh --startup-url https://google.com"), so it fetches and renders untrusted public web content that the agent would read and which could influence its actions.