data-quality-gate

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text indirectly through CI-generated engine artifacts like target/run_results.json, gx/result.json, and scan.log (which include per-check message / FAIL lines) into the runtime collector for gating decisions.