skills/black12-ag/claude-skill/xlsx/Gen Agent Trust Hub

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.py script utilizes subprocess.run to execute system commands including the soffice (LibreOffice) binary and the timeout utility for formula recalculation tasks.\n- [DYNAMIC_EXECUTION]: The recalc.py script 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]: The setup_libreoffice_macro function in recalc.py makes persistent changes to the host environment by writing a macro file into the user's application configuration directories (~/.config/libreoffice or ~/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
Risk Level
MEDIUM
Analyzed
Aug 30, 2026, 02:57 PM
Security Audit — agent-trust-hub — xlsx