run-models

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires fetching and parsing per-model docs and OpenAPI schemas from Replicate (e.g., https://replicate.com/{owner}/{model}/llms.txt and model-specific OpenAPI schemas) — including community/owner-provided models — which are untrusted third-party content the agent must read and use to choose inputs and drive predictions, enabling indirect prompt injection.