skills/anthropics/skills/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • Dynamic Execution & Injection (HIGH): The file scripts/office/soffice.py contains logic to generate a C source file (lo_socket_shim.c), compile it using gcc into a shared object, and then use the LD_PRELOAD environment variable to inject this library into the soffice process. This technique is used to intercept and modify system calls (specifically socket operations) and is considered a high-risk behavior that can be used for privilege escalation or sandbox escapes.
  • Environment Modification & Persistence (MEDIUM): The script scripts/recalc.py automatically writes a LibreOffice Basic macro (Module1.xba) to the user's application configuration directory (e.g., ~/.config/libreoffice/). This modifies the permanent configuration of an external application on the host system to enable automated recalculation and saving of Excel files.
  • Command Execution (LOW): The skill frequently uses subprocess.run to execute external binaries including soffice, gcc, and git. While these calls are parameterized and serve the skill's primary functions, the use of a C compiler (gcc) on dynamically generated source code significantly increases the attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM