xlsx
Warn
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
recalc.pyscript utilizessubprocess.runto execute system commands including thesoffice(LibreOffice) binary and thetimeoututility for formula recalculation tasks.\n- [DYNAMIC_EXECUTION]: Therecalc.pyscript programmatically generates a StarBasic macro (Module1.xba) and writes it to the local file system, subsequently triggering its execution via the office suite.\n- [PERSISTENCE]: Thesetup_libreoffice_macrofunction inrecalc.pymakes persistent changes to the host environment by writing a macro file into the user's application configuration directories (~/.config/libreofficeor~/Library/Application Support/LibreOffice).\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from .xlsx, .xlsm, .csv, and .tsv files, while instructing the agent to study and exactly match patterns found within that data.\n - Ingestion points: Spreadsheet reading operations using pandas and openpyxl as described in
SKILL.md.\n - Capability inventory: System command execution and file system modification capabilities are present in the provided scripts.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used for data ingestion.\n
- Sanitization: The skill does not implement validation or sanitization for content read from external files.
Audit Metadata