power-query-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's Power Query M templates (e.g., Web.Contents calls in references/long-polling-power-query-example.md and rest-api-power-query-example.md using a configurable BaseUrl/ApiUrl) fetch and parse JSON from arbitrary/public Frappe instances or user-provided URLs, meaning the agent will ingest untrusted third‑party content as part of its workflow.