ml-engineering
Warn
Audited by Snyk on Aug 5, 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 runtime workflow in
scripts/check-eval-overlap.pyreads and normalizes free text from user-supplied filesystem paths (--train/--eval) viaPath.read_text()and then computes overlap shingles from that text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata