espn-api

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to construct URLs and fetch/parse JSON from ESPN's public APIs (e.g., site.api.espn.com, sports.core.api.espn.com, now.core.api.espn.com, cdn.espn.com) and follow $ref/search results as part of its workflow, so it ingests open public third‑party content (news, play-by-play, summaries) that the agent must interpret and that can affect subsequent requests/actions.