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 --input path (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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 06:29 PM
Issues
1
Security Audit — snyk — leakage-audit