meeting-prep

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow “Step 3: Research Participants” (via research-workflow.js) uses an agent to perform web searches/LinkedIn checks for each participant and then injects the resulting web-authored free text summaries into the LLM context for compilation (outsider public web content → agent context).