personal-monitor-domain

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests outsider-authored free text from public web content at runtime via the News Feed panel’s RSS/XML parsing and/or GNews/HackerNews headline fetching, which is then passed into the AI Daily Briefing LLM context as “top news headlines” (and potentially email/Feishu snippets too, though those are user-account content rather than public web).