pdf

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

• Third-party content exposure detected (high risk: 0.75). This skill’s runtime workflow (user-provided PDFs processed via pdfplumber.open(...)/page.extract_text() and page.extract_tables()) can ingest outsider-authored free text embedded in PDFs (e.g., documents from others), which the LLM could summarize/use after exec; it does not specifically sanitize or restrict extracted text.