list-building

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is “list building from multiple sources” (e.g., Google Maps scrape, conference attendee files, LinkedIn Sales Nav exports, web search), which at runtime can ingest outsider-authored free-form text from those external/public sources into the agent’s LLM context for processing.