tooluniverse-variant-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries public third-party databases (MyVariant.info, dbSNP, gnomAD, Ensembl VEP, ClinGen, etc.) as shown in SKILL.md Phase 5 and references/annotation_guide.md and in python_implementation.py (batch_annotate_variants / annotate_variant_with_*) — the agent ingests and acts on that external, user-submitted/public data to drive annotation and pathogenicity decisions.