validation-design
Warn
Audited by Snyk on Aug 26, 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). The skill’s runtime helper
scripts/print_folds.pyloads and parses user-provided CSV/Parquet/JSON/JSONL/NDJSON from--inputto compute ordered fold groups, so it ingests outsider-authored free text when an outsider controls that input file.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata