project-status-report

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text from monday.com item content and updates: Step 5 calls get_updates for “Stuck/Blocked” items and Step 5’s fallback reads text from item text/long_text columns (e.g., Notes/Description), which are authored by non-operating users; this text is then summarized into the agent’s LLM context.