momentic-test

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (e.g., calling momentic_session_start and using momentic_preview_step NAVIGATE to the user's baseUrl, plus reading UI-state/screenshot artifacts returned by momentic_get_session_state and preview/run responses) instructs the agent to load and interpret arbitrary webpages (user-supplied or public sites) and use that content to decide/construct test steps, so untrusted third-party page content can materially influence tool actions.