ds-feasibility

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/validate_feasibility.py, the validator CLI reads arbitrary Markdown from the user-supplied study path (run() → read_study_text()), extracts the FEASIBILITY-STUDY-INTERCHANGE fenced YAML block, and then parses/validates it—meaning outsider-authored free text can be directly ingested at runtime.