finngen-phewas-skill

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

• Third-party content exposure detected (high risk: 0.70). The skill's required runtime scripts (scripts/finngen_phewas.py and scripts/variant_resolution.py) perform live HTTP requests to public third‑party APIs (FinnGen at https://r12.finngen.fi and Ensembl at https://rest.ensembl.org / https://grch37.rest.ensembl.org) and parse those JSON responses to resolve variants and drive subsequent outputs, so external content from those public sites can directly influence tool behavior.