fabriciq-ontology-authoring-cli

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes schema discovery by invoking companion skills that query Eventhouse/Kusto (e.g., .show database schema as json) and lakehouse SQL (INFORMATION_SCHEMA.COLUMNS), whose returned results are readable text/JSON that the agent must merge and use in its LLM context—an outsider-authored source (data from external systems) is therefore ingested at runtime.