hygraph

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly allows fetching arbitrary remote URLs ("Create Asset from remote URL") and running GraphQL queries / proxy requests against Hygraph content via Membrane (e.g., "Execute GraphQL Query" and "membrane request"), which ingest user-generated or public third‑party content that the agent is expected to read and could materially influence subsequent actions.