The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF documents which could potentially contain malicious instructions. * Ingestion points: scripts/extract_form_field_info.py, scripts/check_fillable_fields.py, and SKILL.md. * Boundary markers: None identified; the skill directly extracts and processes text content. * Capability inventory: File system access (read/write) and execution of system commands (qpdf, pdftotext). * Sanitization: No sanitization or validation of extracted text is performed before it enters the model context.
[DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py implements a runtime monkeypatch of the pypdf library's DictionaryObject.get_inherited method to correct a known bug in selection list handling.
[COMMAND_EXECUTION]: The skill documentation and scripts facilitate the execution of several PDF utility commands, including qpdf, pdftotext, pdftk, and pdftoppm for document manipulation and rendering.

pdf