platform-abstraction

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

• Third-party content exposure detected (high risk: 0.80). The skill's examples use the HttpClient service to fetch and parse external URLs (e.g., client.get("https://api.example.com/users") / response.json), which means the agent can ingest untrusted third‑party web content as part of its workflow.