pdf

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py implements a runtime monkeypatch of the pypdf.generic.DictionaryObject.get_inherited method. This is used to resolve a specific data type handling bug in pypdf version 5.7.0 when processing selection list fields.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external PDF files using various methods (direct text extraction, OCR, and table parsing). This represents an attack surface for indirect prompt injection, where content within a PDF could attempt to influence the agent's logic.
  • Ingestion points: PDF files processed via pypdf, pdfplumber, and pytesseract (documented in forms.md and SKILL.md).
  • Boundary markers: Not explicitly implemented in the provided extraction scripts.
  • Capability inventory: The skill can read/write local files and manipulate document structure, but does not have native network capabilities.
  • Sanitization: No specific sanitization or filtering is performed on the extracted text before it is presented to the agent.
  • [COMMAND_EXECUTION]: The documentation and guide reference multiple system utilities (e.g., qpdf, poppler-utils, pdftk) for advanced PDF operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:52 PM