The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF files for text extraction, OCR, and form field analysis, which provides a surface for indirect prompt injection attacks.
Ingestion points: Untrusted data enters the context through scripts/extract_form_field_info.py, scripts/convert_pdf_to_images.py, and text extraction examples in SKILL.md.
Boundary markers: The skill does not use specific delimiters or instructions to the agent to ignore potentially malicious embedded content within the PDFs.
Capability inventory: The skill can read and write files and execute local scripts as instructed in forms.md.
Sanitization: Extracted text and visual data are not sanitized or filtered before being processed by the agent.
[DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py performs runtime monkeypatching on the pypdf library.
Evidence: It modifies the get_inherited method of the DictionaryObject class in pypdf.generic to fix a bug in how the library handles selection list fields. While this is used for legitimate troubleshooting, runtime code modification is a dynamic execution pattern.

pdf