pydantic-evals

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

• Third-party content exposure detected (high risk: 0.70). The skill's documentation includes a concrete custom evaluator example (references/evaluator-types.md "APIResponseValid") that performs an HTTP GET to an arbitrary api_endpoint using httpx and then uses that external response to validate agent outputs, which clearly fetches and ingests untrusted third‑party content as part of the evaluation workflow.