khe-brain-yc

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only reads bundled, first-party reference files, except when a user links a page not in the sources table, which the Refresh path requires the agent to fetch and read, so outsider-authored text is ingested only after the agent fetches a user-selected URL.