The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides several Python scripts (word_processor.py, excel_processor.py, batch_processor.py) designed to be executed via the command line to perform operations like reading, writing, and merging Office documents.\n- [EXTERNAL_DOWNLOADS]: The skill depends on standard, industry-standard Python libraries including python-docx, openpyxl, and pandas to handle document manipulation and data analysis.\n- [PROMPT_INJECTION]: The skill processes untrusted content from external Office documents and JSON files, which creates an attack surface for indirect prompt injection where malicious instructions could be embedded in data processed by the AI.\n
Ingestion points: scripts/word_processor.py (line 21, read_document), scripts/excel_processor.py (line 21, read_excel), and scripts/batch_processor.py (line 25, batch_fill_templates).\n
Boundary markers: Absent. The scripts extract raw text and data without wrapping them in delimiters or including instructions for the agent to ignore embedded commands.\n
Capability inventory: The skill has the capability to read and write arbitrary files on the local file system (limited by execution environment permissions).\n
Sanitization: Absent. The skill performs direct text extraction and simple string substitution for template filling without sanitizing or escaping the processed content.

office-automation