browser-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill issues browser commands that navigate to arbitrary public URLs (e.g., "browser navigate ", examples like techcrunch.com and Google) and uses browser extract/Stagehand to read and interpret page content, so it clearly ingests untrusted third‑party web content as part of its workflow.