The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources (Excel and CSV files), which creates a potential surface for indirect prompt injection if the files contain malicious instructions.
Ingestion points: The skill uses load_workbook() and csv.reader() to import data from external files into the agent's context.
Boundary markers: The skill does not specify any delimiters or instructions for the agent to ignore or isolate instructions found within the processed spreadsheet data.
Capability inventory: The agent uses file-system access (read/write) and Python code execution capabilities to process and manipulate the spreadsheet data.
Sanitization: There is no evidence of input validation, filtering, or sanitization of the content loaded from external files before it is processed.
[EXTERNAL_DOWNLOADS]: The documentation references the installation of the openpyxl library via pip and points to its repository on GitHub. These are recognized as well-known and standard development resources.
[COMMAND_EXECUTION]: The skill's primary function involves the agent dynamically generating and executing Python code for spreadsheet manipulation, which is consistent with the skill's stated purpose.

xlsx-manipulation