skills/michaelboeding/skills/pdf/Gen Agent Trust Hub

pdf

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external PDF documents, which serves as an attack surface for instructions meant to influence agent behavior.
  • Ingestion points: The skill uses pypdf.PdfReader in several scripts (e.g., scripts/extract_form_field_info.py, scripts/fill_fillable_fields.py) and pdfplumber.open in SKILL.md to read content from user-provided PDF files.
  • Capability inventory: The skill possesses capabilities to write files (writer.write), execute shell commands (qpdf, pdftk), and generate images from PDF pages.
  • Boundary markers: While forms.md establishes a structured fields.json workflow to handle form data, the agent still processes raw text extracted from the document body.
  • Sanitization: There is no evidence of explicit sanitization or filtering of text extracted from PDFs before it is processed by the AI agent context.
  • [DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py performs runtime modification of the pypdf library, known as monkeypatching.
  • Evidence: The function monkeypatch_pydpf_method redefines DictionaryObject.get_inherited to correct a specific bug in selection list handling within pypdf version 5.7.0.
  • [COMMAND_EXECUTION]: The skill instructions facilitate the execution of various command-line utilities for PDF processing.
  • Evidence: SKILL.md and reference.md provide usage examples for qpdf, pdftk, and poppler-utils (pdftotext, pdftoppm, pdfimages) which require shell execution privileges.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 06:28 AM