Warn
Audited by Snyk on Feb 15, 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 explicitly ingests and reads user-supplied PDFs (e.g., Phase 2-A "PDF 읽기/추출" using pypdf/pdfplumber on the specified 원본 PDF 경로 / input.pdf), meaning the agent will parse arbitrary untrusted third‑party content.
Audit Metadata