brenda-database

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples set EMAIL and PASSWORD (and compute PASSWORD_SHA256) as variables and pass them directly into SOAP calls, which requires the agent to handle and potentially output user credentials verbatim (even though env-var advice is mentioned elsewhere).

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow calls BRENDA’s SOAP API at runtime (e.g., client.service.getKmValue/getTurnoverNumber/getInhibitors), ingesting outsider-authored free-text fields like commentary, inhibitor, organism, and literature from the public BRENDA service into the agent’s LLM context via the returned SOAP response.