xlsx-official
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
recalc.pyscript invokes thesoffice(LibreOffice) binary usingsubprocess.runto perform headless operations on spreadsheet files. This is a functional requirement for the skill's formula recalculation feature. - [DYNAMIC_EXECUTION]: The skill dynamically generates a LibreOffice Basic macro file and writes it to the local application configuration directory. This macro is used to automate the recalculation and saving process. The generated code is static and does not incorporate untrusted external input.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Excel files, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Data enters the agent's context through
pandas.read_excelandopenpyxl.load_workbookas specified inSKILL.md. - Boundary markers: There are no instructions to use delimiters or ignore potentially malicious instructions embedded in spreadsheet cells.
- Capability inventory: The skill allows the agent to write files and execute local Python scripts capable of running system commands.
- Sanitization: The skill does not provide mechanisms for validating or sanitizing the content of the spreadsheet cells before they are processed by the agent.
Audit Metadata