opentargets-database

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

• Third-party content exposure detected (high risk: 0.70). The skill directly queries the public Open Targets GraphQL API (https://api.platform.opentargets.org/api/v4/graphql) and ingests third‑party evidence and literature fields (e.g., Europe PMC text‑mining, GWAS Catalog, ClinVar) from public data sources which the agent is expected to read and interpret as part of its workflows, exposing it to untrusted external content.