locus-to-gene-mapper-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill autonomously fetches and ingests data from multiple public third‑party APIs (e.g., GWAS Catalog at https://www.ebi.ac.uk/gwas/rest/api, EFO OLS at https://www.ebi.ac.uk/ols4/api, Open Targets GraphQL at https://api.platform.opentargets.org/api/v4/graphql, gnomAD and NCBI RefSNP endpoints) and uses those untrusted responses (traits, synonyms, credible sets, L2G/coloc/eQTL rows, etc.) as direct inputs that determine anchor selection, scoring, and downstream actions, so external content can materially influence agent behavior.