PassAudited by ClawScan on Apr 15, 2026.
Overview
The skill's code, instructions, and requested resources are consistent with a PDF manipulation toolkit — nothing requests unrelated credentials or network access, but you should review and install the required Python and system dependencies before use and treat untrusted PDFs cautiously.
This skill appears coherent with its stated purpose, but before installing or running it: (1) Review and install the required dependencies yourself — both Python packages (pypdf, pdfplumber, reportlab, pdf2image, pytesseract, etc.) and system packages (poppler-utils, tesseract, qpdf/pdftk as needed). The SKILL.md and scripts reference these but there is no automated installer. (2) The code monkey-patches pypdf behavior as a workaround; this is a brittle but disclosed hack — be prepared for viewer quirks and test on non-sensitive documents first. (3) Treat untrusted PDFs with care: parsing complex PDFs can expose parser vulnerabilities or hidden JavaScript in PDFs; run on a sandbox or isolated environment if you will process files from unknown sources. (4) If you need networked or server-side use, verify where you host dependencies and keep them up-to-date. If you want, I can produce a checklist of exact packages/versions and system commands to prepare a safe environment for running these scripts.