office-word
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides utility scripts for document format conversion as described. No malicious behavior was detected.
- [EXTERNAL_DOWNLOADS]: Uses the
python-docxlibrary, which is a well-known package from the Python Package Index (PyPI). - [PROMPT_INJECTION]: The skill processes content from
.docxfiles, which presents an indirect prompt injection surface. This allows external document content to enter the agent's context. - Ingestion points:
scripts/read_docx.pyreads content from file paths provided by the user. - Boundary markers: Absent; content is converted to Markdown and returned directly.
- Capability inventory: The agent has capabilities to read/write files and execute shell commands.
- Sanitization: No content filtering is applied to the extracted text.
Audit Metadata