continue-deep-research

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests and inspects arbitrary outsider-authored free text provided by the user at runtime (e.g., pasted notes/drafts, attached/local files, and supplied URLs/source lists), and later may browse/search and read primary sources referenced by that supplied material.