The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to extract text and tables from external PDF documents using libraries like pypdf, pdfplumber, and pytesseract. This creates a surface for indirect prompt injection where instructions embedded in a processed PDF could attempt to influence the agent's behavior.
Ingestion points: PDF extraction logic in SKILL.md via PdfReader, pdfplumber.open(), and pytesseract.image_to_string().
Boundary markers: Not present; extracted text is concatenated or printed directly to the agent's context without delimiters or warnings.
Capability inventory: The skill includes capabilities for file system writing (creating new PDFs and Excel files) and execution of specific PDF-related command-line utilities (qpdf, pdftk, pdftotext).
Sanitization: No sanitization or validation of the extracted PDF content is implemented before it is processed by the agent.
[COMMAND_EXECUTION]: The skill documents the use of standard command-line utilities such as pdftotext, qpdf, and pdftk for document processing tasks. These are restricted to specific PDF operations and do not involve arbitrary command execution or shell injection from untrusted inputs.

pdf