skills/tassiovale/claude-code-kit/pdf/Gen Agent Trust Hub

pdf

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides a robust set of instructions and scripts for handling PDF operations. The codebase uses well-established libraries such as pypdf, pdfplumber, and Pillow in a standard manner consistent with its stated purpose of PDF processing.
  • [COMMAND_EXECUTION]: The documentation instructs the agent to use several command-line tools for PDF and image manipulation, including qpdf, pdftk, pdftotext, pdfimages, pdftoppm, and magick (ImageMagick). These are standard utilities for the tasks described and are used appropriately within the skill's workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references and encourages the installation of well-known third-party libraries and system packages, such as pytesseract, pdf2image, reportlab, pypdfium2, pdf-lib, and pdfjs-dist. These dependencies are standard in the PDF processing ecosystem.
  • [SAFE]: The script scripts/fill_fillable_fields.py implements a runtime monkeypatch of the pypdf library's DictionaryObject.get_inherited method. This modification is used to normalize the format of choice field options and does not exhibit any suspicious or dangerous behavior.
  • [PROMPT_INJECTION]: As the skill is designed to process external PDF files, it possesses an inherent surface for indirect prompt injection. The agent extracts text and tables from untrusted documents using pdfplumber and pypdf without explicit sanitization, which is typical for this type of utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:23 AM