polish-language

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

• Third-party content exposure detected (medium risk: 0.30). SKILL’s required runtime workflow reads the user-provided manuscript text and (optionally) scans figure source files under a provided figures directory (via scripts/lint_consistency.py and scripts/lint_figure_locale.py), so outsider-authored text can be supplied through the manuscript/figures themselves.