gologin-agent-browser-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly allows opening arbitrary public URLs via agent_browser_open (see SKILL.md, tools.md, and examples/quick-session.md) and uses snapshot/get/find to read page content and drive clicks/typing, so untrusted third-party webpages can be ingested and influence subsequent agent actions.