tooluniverse-spatial-omics-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls public third-party APIs and databases (e.g., OpenTargets_get_disease_id_description_by_name in Phase 0, HPA_get_rna_expression_by_source and HPA_get_comprehensive_gene_details in Phase 1/6, STRING_functional_enrichment in Phase 2, and PubMed_search_articles/openalex_literature_search in Phase 8) as required steps and ingests their outputs to compute scores, identify druggable targets, and drive analysis decisions, so untrusted external content can materially influence agent behavior.