central-station

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and displays user-generated Central Station community threads from public endpoints (e.g., https://station-server.railway.com/api/llms-station, the GraphQL https://station-server.railway.com/gql, and thread markdown at https://station.railway.com/{topic}/{thread}.md), so the agent ingests untrusted third-party content that could contain indirect prompt injections.