schema-composition

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

• Third-party content exposure detected (high risk: 0.80). The skill includes an async transformation example that performs a fetch from a public API (get(https://swapi.dev/api/people/${s}) in the "Async Transformations" section), which demonstrates ingesting untrusted third-party content that the agent would read/interpret as part of its workflow.