The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill's primary function involves the agent generating and executing a Python script using the python-docx library to create binary Word files. It also includes a local helper script, scripts/docx_tool.py, which performs file operations and XML manipulation using standard libraries.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, such as document briefs or source content, which is used to generate the final document. This creates a surface for indirect prompt injection if the user-supplied text contains instructions intended to influence the agent's behavior during the drafting phase.
Ingestion points: User-provided document content, briefs, and placeholders passed to scripts/docx_tool.py via command-line arguments or standard input.
Boundary markers: None identified; user content is processed directly to build the document structure.
Capability inventory: The skill allows the agent to write and execute Python scripts, write binary .docx files to the local file system, and read existing document templates.
Sanitization: The provided Python script uses xml.sax.saxutils.escape to ensure the generated XML is well-formed, but there is no specific sanitization to prevent the agent from following instructions embedded in the user's input.

word-document