xlsx
Warn
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The file
scripts/office/soffice.pycontains an embedded C source string (_SHIM_SOURCE) which is written to a temporary file and compiled into a shared library at runtime usinggcc. This library is then injected into the LibreOffice (soffice) process via theLD_PRELOADenvironment variable to modify its socket behavior. - [DYNAMIC_EXECUTION]: The file
scripts/recalc.pydynamically generates a LibreOffice Basic macro and writes it to the user's application configuration directory (e.g.,~/.config/libreoffice/4/user/basic/Standard/Module1.xba). This macro is subsequently invoked via avnd.sun.star.scriptURI to automate formula recalculation. - [COMMAND_EXECUTION]: Several components execute shell commands using the
subprocessmodule: scripts/office/soffice.pyrunsgccfor compilation and executes thesofficebinary.scripts/recalc.pyexecutessoffice, as well astimeoutorgtimeoutfor process control.scripts/office/validators/redlining.pyexecutesgit diffto compare text content within documents.- [PERSISTENCE_MECHANISMS]:
scripts/recalc.pyinstalls a macro into the host's LibreOffice configuration directory. This modification persists on the filesystem and affects the LibreOffice environment across different sessions. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection as it processes untrusted tabular data.
- Ingestion points: External spreadsheet files (.xlsx, .csv, etc.) are read into the agent context using
pandasandopenpyxlas described inSKILL.md. - Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions embedded within the spreadsheet cells.
- Capability inventory: The skill can execute arbitrary commands (via
recalc.pyandsoffice.py), write to the filesystem, and modify application configuration files. - Sanitization: While the skill uses
defusedxmlto mitigate some XML-related attacks (like XXE), it does not sanitize or filter the actual data content from cells before it is processed by the agent.
Audit Metadata