brenda-database

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

• Third-party content exposure detected (high risk: 0.70). This skill directly queries the public BRENDA SOAP API (e.g., https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl) via functions like get_km_values and get_reactions and parses/commentary fields from those external responses, so it ingests and interprets third‑party public content at runtime.