The Agent Skills Directory

[PROMPT_INJECTION]: The skill's primary function is extracting data and text from external PDF documents using pypdf, pdfplumber, and OCR tools like pytesseract. This workflow is inherently susceptible to indirect prompt injection, where a malicious document could contain instructions designed to override the agent's behavior.
Ingestion points: Text extraction occurs in SKILL.md examples and via scripts/extract_form_field_info.py which reads field names and metadata.
Boundary markers: The instructions in forms.md do not provide clear delimiters or 'ignore instructions' warnings when the agent processes extracted text.
Capability inventory: The agent has the ability to read/write files and execute the provided Python scripts in the scripts/ directory.
Sanitization: There is no evidence of sanitization or filtering of the content extracted from the PDFs before it is returned to the agent.
[COMMAND_EXECUTION]: The skill relies on the execution of multiple localized Python scripts and system-level binaries (e.g., qpdf, pdftotext, pdftk) to perform its tasks. The forms.md file provides specific command-line instructions for the agent to follow.

pdf