The Agent Skills Directory

[SAFE]: The skill's instructions and provided code snippets are consistent with its stated goal of spreadsheet manipulation. No security violations or malicious behaviors were detected.
[COMMAND_EXECUTION]: The skill utilizes a local script, scripts/recalc.py, to recalculate Excel formulas via LibreOffice. This is a legitimate operational step for ensuring spreadsheet accuracy and is initiated through standard shell commands.
[PROMPT_INJECTION]: The skill processes untrusted spreadsheet data, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: The skill reads .xlsx, .csv, and .tsv files using pandas and openpyxl (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to ignore or isolate potential instructions embedded within cell contents.
Capability inventory: The skill can write files to the local file system and execute a local Python script for formula recalculation.
Sanitization: No data validation or sanitization routines are specified for handling the content retrieved from external files.

xlsx