gather-business-context

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

• Third-party content exposure detected (high risk: 0.70). This skill’s required workflow is a retrieval/extraction process (“Search…”, “Extract…”, “Return…with citations”), which at runtime can ingest free-form text from enabled/provided external sources (e.g., public web pages, outsider-authored docs/messages) into the agent’s LLM context.