The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions to execute a specific Python script to validate Excel formulas.
Evidence: python /mnt/skills/public/xlsx/recalc.py model.xlsx in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied Excel templates and assumptions, creating a potential vector for indirect instructions.
Ingestion points: examples/LBO_Model.xlsx and user-provided template files.
Boundary markers: Absent; there are no instructions to differentiate data from commands within the processed files.
Capability inventory: The agent can modify Excel workbooks and execute a local Python utility script.
Sanitization: Absent; the skill does not specify procedures for cleaning or validating ingested template data.

lbo-model