fetch

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

• Third-party content exposure detected (high risk: 0.90). The skill provides an HTTP client (api.get/post etc.) that accepts arbitrary base URLs and will fetch and return responses from third-party web endpoints (see "Inputs to Request" and api.get(url, schema)), meaning the agent can ingest untrusted public/web content that could carry indirect prompt injection.