tooluniverse-polygenic-risk-score

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries and ingests public, third‑party GWAS data (e.g., GWAS Catalog via gwas_get_associations_for_trait and OpenTargets via OpenTargets_search_gwas_studies_by_disease) as documented in SKILL.md "Data Sources" and implemented in python_implementation.py's build_polygenic_risk_score, and those external association records and effect sizes are parsed and directly drive PRS construction and downstream decisions, so untrusted third‑party content can materially influence agent behavior.