nvidia-kaggle-skill

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow for Kaggle Discussions ingests outsider-authored free text (discussion titles/bodies and commentMarkdown) from Kaggle discussion threads into data/discussions.db via discussion_ingest.py, and later prints that stored text via discussion_read.py.