review-extraction

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). In scripts/build_golden_slice_bundle.py, the runner extracts and embeds free-text fields from the PDF it is given (_extract_page() reads block.get("text") and table.get("text"/"markdown")) into the generated evidence bundle and the closure HTML (_render_evidence()/_build_closure_signoff() use el.get("text") for previews and element notes).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 06:03 PM
Issues
1
Security Audit — snyk — review-extraction