skills/billylui/skills/xlsx/Gen Agent Trust Hub

xlsx

Warn

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONSAFE
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/office/soffice.py hardcodes C source code and compiles it at runtime into a shared object library using gcc. This library is stored in the system's temporary directory.- [COMMAND_EXECUTION]: The skill utilizes the LD_PRELOAD environment variable to perform library injection into the soffice (LibreOffice) process, overriding standard socket behaviors to bypass sandbox restrictions.- [COMMAND_EXECUTION]: The skill invokes several system binaries via subprocesses, including soffice for spreadsheet processing, gcc for runtime compilation, and git for document content comparison.- [PERSISTENCE]: The scripts/recalc.py script writes a persistent StarBasic macro to the application's configuration directory on the host system. This macro remains present in the LibreOffice environment across sessions to facilitate the recalc feature.- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it ingests and processes untrusted data from external spreadsheet files (.xlsx, .csv, .tsv) and evaluates formulas within them. Evidence: 1. Ingestion points: pandas.read_excel and openpyxl.load_workbook in SKILL.md and scripts/recalc.py. 2. Boundary markers: Absent. 3. Capability inventory: Subprocess calls to soffice and gcc, file write operations across multiple scripts. 4. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 03:13 AM