opentargets-database

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly queries and ingests data from the public Open Targets GraphQL API (https://api.platform.opentargets.org/api/v4/graphql) in its required workflows (SKILL.md examples) and uses that returned evidence/literature/drug data to rank targets and drive decisions, so untrusted third‑party content could materially influence agent behavior.