tooluniverse-antibody-engineering

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow and code examples (Phase 0 tool list and multiple functions in SKILL.md/REFERENCE.md) explicitly call external public resources such as IMGT_search_genes/IMGT_get_sequence, SAbDab_search_structures, TheraSAbDab_search_by_target, iedb_search_epitopes, UniProt_get_protein_by_accession and PubMed_search, which fetch and ingest third‑party public site data that the agent reads and uses to drive design decisions—creating a clear pathway for untrusted external content to influence actions.