The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF documents, creating a surface for indirect prompt injection where malicious instructions could be hidden in document content or metadata.
Ingestion points: PDF data is ingested by scripts/extract_form_field_info.py, scripts/fill_fillable_fields.py, and scripts/convert_pdf_to_images.py to extract text and form metadata.
Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands when processing the extracted PDF data.
Capability inventory: The skill possesses capabilities to read/write files and execute command-line tools for PDF processing.
Sanitization: No explicit sanitization or filtering of PDF content is performed; the skill relies entirely on the underlying library's (pypdf) parsing safety.
[DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py implements a runtime monkeypatch to modify the behavior of the pypdf library.
Evidence: The monkeypatch_pydpf_method function dynamically replaces DictionaryObject.get_inherited with a custom implementation to fix a known bug in selection list handling. While used here for legitimate bug-fixing, runtime modification of library code is a dynamic execution pattern.

pdf