The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external PDF files, creating a surface for indirect prompt injection attacks where malicious document content could attempt to influence the agent's behavior.
Ingestion points: External PDFs are processed via scripts/extract_form_field_info.py, scripts/convert_pdf_to_images.py, and scripts/check_fillable_fields.py.
Boundary markers: The skill does not employ explicit boundary markers or specific instructions to the agent to treat extracted PDF content as untrusted data.
Capability inventory: The skill allows file system access (read/write) and the execution of provided Python scripts and command-line tools.
Sanitization: Extracted text and metadata are not sanitized or filtered for instructional content before being processed by the agent.
[DYNAMIC_EXECUTION]: The script scripts/fill_fillable_fields.py modifies the execution environment at runtime to resolve a library-specific bug.
Evidence: The monkeypatch_pydpf_method function dynamically replaces pypdf.generic.DictionaryObject.get_inherited with a custom implementation.

pdf