validating-external-data

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and parses data from public HTTP APIs (for example the fetch to https://jsonplaceholder.typicode.com/posts/${id}) and lists HTTP APIs/WebSocket messages/files as system boundaries, so it clearly ingests untrusted third‑party content as part of its workflow.