bonsai-impl-classification

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes the bSDD online lookup path, where the agent calls bsdd.Client.search_class() / get_class() at runtime and ingests the returned bSDD JSON fields (e.g., class names/properties) as readable text into the LLM context, creating an indirect prompt-injection risk from outsider-controlled web/API content.