docx
Warn
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill employs dynamic code generation and process injection techniques to handle document conversion.
- Runtime Compilation: The script
scripts/office/soffice.pyhardcodes C source code, writes it to a temporary file, and compiles it at runtime usinggcc. The resulting shared object is then loaded into the execution environment viaLD_PRELOADto shim socket system calls. - Macro Injection:
scripts/accept_changes.pydynamically creates a LibreOffice Basic macro and installs it into a temporary user profile to automate document modification tasks. - [COMMAND_EXECUTION]: Multiple components execute system binaries and shell commands via the subprocess module.
- System Tools: Scripts invoke external binaries including
gccfor compilation,soffice(LibreOffice) for document processing,gitfor text diffing, andpdftoppmfor image conversion. - Scope: Command execution is used extensively across
scripts/office/soffice.py,scripts/accept_changes.py, andscripts/office/validators/redlining.py. - [EXTERNAL_DOWNLOADS]: The skill instructions specify requirements for third-party libraries and software.
- Node.js Dependencies:
SKILL.mdrequires the global installation of thedocxlibrary vianpm install -g docx. - System Dependencies: The skill relies on external tools being present in the environment, specifically
pandoc,LibreOffice, andPoppler. - [PROMPT_INJECTION]: The skill architecture is susceptible to indirect prompt injection through document ingestion.
- Ingestion Points:
scripts/office/unpack.pyextracts raw XML and text from user-provided documents and integrates it into the agent's context. - Boundary Markers: Document content is processed without protective delimiters or instructions for the agent to disregard embedded commands.
- Capability Inventory: The agent's access to high-privilege tools (Bash, subprocess execution) creates a risk should malicious instructions be found in the ingested document data.
- Sanitization: No sanitization or safety filtering is performed on the extracted XML content before processing.
Audit Metadata