synthesis-application

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow ingests extracted_components and purpose_context provided by the calling agent; if those extracted components include outsider-authored free text (e.g., issue/PR/wiki/discussion body text or scraped web page content) then that prose is fed into the LLM for the completeness/logic/applicability checks.