structured-extraction

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

• Third-party content exposure detected (low risk: 0.10). The required runtime path ingests user-provided “text” as the extraction input in the form of an LLM prompt, but it does not ingest any outsider-authored text from monitored external feeds/queues/tickets; the only free text exposure is the caller-supplied document content passed directly as the content/text input for constrained decoding.