skills/zebbern/claude-code-guide/pdf/Gen Agent Trust Hub

pdf

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing several industry-standard libraries for PDF processing, such as pypdf, pdfplumber, reportlab, pytesseract, pdf2image, pypdfium2, pdf-lib, and pdfjs-dist.
  • [COMMAND_EXECUTION]: The skill instructions provide command-line examples for common PDF tasks using widely-used tools like qpdf, pdftotext, pdftk, and magick (ImageMagick).
  • [PROMPT_INJECTION]: The skill is designed to extract and process text from external PDF files, which introduces an inherent surface for indirect prompt injection.
  • Ingestion points: SKILL.md (text extraction snippets) and scripts/extract_form_structure.py (label extraction).
  • Boundary markers: None identified in the provided extraction logic or prompt templates.
  • Capability inventory: The skill includes capabilities for file system writes (writer.write) and shell command execution (qpdf, pdftotext).
  • Sanitization: No explicit sanitization or filtering of extracted document content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 02:07 AM
Security Audit — agent-trust-hub — pdf