pdf

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions for installing standard PDF processing libraries and system utilities such as pypdf, pdfplumber, reportlab, pytesseract, pdf2image, pypdfium2, and poppler-utils via official package repositories.
  • [COMMAND_EXECUTION]: The documentation provides examples for using established command-line tools for PDF manipulation, including qpdf, pdftotext, pdftk, and pdfimages.
  • [PROMPT_INJECTION]: The skill is designed to process external PDF files, which is an intended functionality that introduces an indirect prompt injection surface.
  • Ingestion points: Untrusted PDF documents are processed by scripts such as scripts/extract_form_field_info.py and scripts/fill_fillable_fields.py.
  • Boundary markers: The skill does not currently implement explicit boundary markers for the data extracted from PDF files.
  • Capability inventory: The skill can execute shell commands and perform file system writes as part of its document processing workflows.
  • Sanitization: The skill processes the structural components and text of PDF files without explicit sanitization of the embedded content.
  • [SAFE]: The script scripts/fill_fillable_fields.py utilizes a runtime monkeypatch of the pypdf library to fix a specific bug in selection list processing, ensuring correct form field functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 09:14 PM
Security Audit — agent-trust-hub — pdf