brenda-database

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries the public BRENDA SOAP API (see SKILL.md and references/api_reference.md with the WSDL https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl) and the provided scripts (e.g., scripts/brenda_queries.py and scripts/enzyme_pathway_builder.py) parse and act on those external responses (get_km_values/get_reactions) to drive enzyme selection, pathway construction, and plotting, so third‑party content can materially influence agent decisions.