bioservices

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

• Third-party content exposure detected (high risk: 0.80). This skill programmatically fetches and parses data from open public bioinformatics services (e.g., UniProt via u.search/u.retrieve, KEGG via k.get/parse_kgml_pathway, NCBIblast run/getResult, QuickGO, PSICQUIC, etc.), so the agent will ingest untrusted third‑party web content as part of its workflow.