metabase-react-sdk-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses user-provided Metabase content via the instance API (e.g., /api/search and /api/automagic-dashboards) and uses those user-generated dashboards to decide which items to embed and how to generate code (and also fetches versioned docs from https://www.metabase.com/docs/v0./llms.txt), so untrusted third-party content is ingested and can materially influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly curls https://www.metabase.com/docs/v0./llms.txt (with fallback to https://www.metabase.com/docs/latest/llms.txt) at runtime and requires using that document as the authoritative source for auth setup, API shapes, install commands, and generated code, so the fetched remote content directly controls the agent's instructions and is a required dependency.