pdf

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed plaintext passwords in commands and code (e.g., qpdf --password=mypassword and writer.encrypt("userpassword","ownerpassword")), which would require emitting secret values verbatim and is therefore insecure.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and processes arbitrary user-supplied PDFs (e.g., PdfReader("document.pdf"), pdfplumber extract_text, extract_form_field_info.py, convert_pdf_to_images.py, and fill_pdf_form_with_annotations.py), so the agent ingests and interprets untrusted third‑party/user-provided PDF content as part of its workflow.