NYC

document-rag-pipeline

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill ingests and processes arbitrary PDF files from a user-specified folder (see build_inventory scanning Path(args.folder) and process_documents calling extract_pdf_text/ocr_pdf) and reads/chunks those documents into the semantic search results, so untrusted third-party or user-provided content could be interpreted by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:36 AM