The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation explicitly instructs the agent to execute a shell command python scripts/recalc.py to recalculate formulas in Excel workbooks.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external spreadsheet data from .xlsx, .csv, and .tsv files. Ingestion points: Files are read into the environment using pd.read_excel and load_workbook as described in SKILL.md. Boundary markers: The instructions do not include markers or warnings to distinguish between user instructions and data content. Capability inventory: The skill has the ability to write files to the filesystem and execute local Python scripts via the shell. Sanitization: No sanitization or validation of the ingested spreadsheet data is mentioned or implemented in the provided documentation.

xlsx