The Agent Skills Directory

[SAFE]: The skill provides legitimate instructions and code snippets for data analysis tasks using industry-standard Python libraries. All code examples are focused on the primary purpose of processing spreadsheet data locally.
[PROMPT_INJECTION]: The skill provides patterns for reading untrusted data from Excel spreadsheets which creates an attack surface for indirect prompt injection. However, this is a necessary part of the skill's intended functionality.
Ingestion points: pd.read_excel used throughout SKILL.md to load external files.
Boundary markers: Not present in example code snippets.
Capability inventory: Local file writing via to_excel and plt.savefig.
Sanitization: None provided in the examples.

excel-analysis