databricks-docs

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses WebFetch to retrieve https://docs.databricks.com/llms.txt (public web content) and then fetches specific documentation pages, so outsider-authored free text from the Databricks website is ingested into the agent’s LLM context.