The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill scripts or documentation.
[COMMAND_EXECUTION]: The skill uses subprocess.run to call soffice (LibreOffice) and pdftoppm (Poppler) for document conversion. This is part of the intended functionality and uses secure coding practices (argument list format) to prevent shell injection.
[EXTERNAL_DOWNLOADS]: The skill relies on well-known and reputable Python packages including python-docx and Pillow. These are standard tools for its stated purpose.
[PROMPT_INJECTION]: As the skill processes user-provided DOCX files for translation, it possesses an indirect prompt injection surface. This is a low-risk concern inherent to the skill's primary function of document analysis.
Ingestion points: REFERENCE.md, utils/create_translation.py, and utils/verify_document.py.
Boundary markers: Absent.
Capability inventory: REFERENCE.md executes soffice and pdftoppm.
Sanitization: Absent.

rtl-document-translation