pdf

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed plaintext passwords directly into command-line arguments and function calls (e.g., --password=mypassword and writer.encrypt("userpassword","ownerpassword")), which would require the agent to handle or reproduce secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is ingested when a user-provided PDF is parsed at runtime (e.g., labels/checkbox text extracted via pdfplumber in scripts/extract_form_structure.py, or field names/content read via PdfReader.get_fields() in scripts/extract_form_field_info.py), and that extracted text then flows into downstream JSON/annotation generation.