device-assistant

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow for error lookup uses search_error_code (web lookup) and includes an attacker-controlled error_code/manufacturer/model in the constructed query/searchUrl, but it does not ingest arbitrary outsider-authored free text content itself (it only prepares a Google search link/structured fields when no built-in match exists).