leakage-audit
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 required runtime workflow (“audit_pregame_features.py”) ingests an outsider-provided modeling table via the
--inputpath (CSV/Parquet/JSON/JSONL/NDJSON) and the LLM consumes/acts on free text contained in that file (e.g., column names and report text derived from it).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata