tooluniverse-structural-variant-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md and REFERENCE.md) instructs the agent to query and ingest results from public third-party resources—e.g., ClinVar, gnomAD, DECIPHER, PubMed/EuropePMC, OMIM, and DisGeNET—whose user-submitted or public records are read and explicitly used to drive ACMG classification and downstream actions, creating a clear vector for indirect prompt injection.