The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python and the pandas library to perform file system operations, such as reading input spreadsheets and writing a consolidated output file.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources. Ingestion points: Content is read from CSV, Excel, and TSV files via pd.read_csv and pd.read_excel. Boundary markers: None; the skill does not use specific delimiters to isolate processed data from the prompt context. Capability inventory: Includes file system access and script execution capabilities. Sanitization: No content sanitization is performed on the data values within the spreadsheets. While this creates a potential surface for indirect prompt injection, the risk is minimized as the skill logic focuses on structural data management rather than interpreting content as instructions.
[SAFE]: No malicious patterns such as obfuscation, credential harvesting, or unauthorized network operations were detected. The use of standard libraries for their intended purpose is appropriate.

csv-excel-merger