kaggle-research
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In
scripts/kaggle_runtime/smoke.py:run_readonly_smoke(live-readonly verification), the workflow ingests free text from Kaggle CLI outputs—specifically the dataset search CSV (execute(... "datasets list" ...)then parsed by_csv_rowsand_dataset_candidates)—which could include outsider-authored content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata