agent-browser

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses agent-browser open <url> and then agent-browser snapshot -i / get text body / eval to ingest readable DOM text from the opened page (public web content or other outsiders’ pages), which can include attacker-controlled free text that becomes part of the LLM context via the snapshot/output.