tooluniverse-gwas-snp-interpretation

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly queries public third-party APIs (GWAS Catalog and Open Targets Genetics) as part of its runtime workflow — see SKILL.md "Data Sources" and python_implementation.py which calls gwas_get_snp_by_id, gwas_get_associations_for_snp, and OpenTargets_get_variant_credible_sets — and it interprets those results to generate clinical significance and downstream decisions, so untrusted external content can materially influence behavior.