eudic-to-anki

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly imports user/third-party content from the Eudic cloud via scripts/eudic_export.py (see SKILL.md Quick Start step 3 and modules/export/README.md), preserves exported context_line as source_context in build_dia_json_from_csv.py, and requires the agent to read and use that source_context when authoring coach JSON and driving downstream imports, so untrusted external text can directly influence agent behavior.