The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script and several external command-line utilities to maintain project documentation.
The script scripts/gen-ref-pages.py is executed to programmatically generate markdown reference pages from source code.
The agent is directed to use rumdl for docstring formatting and mise for project tasks such as linting and building documentation.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it treats external source code and existing docstrings as the primary source of information for its tasks.
Ingestion points: Python source files (.py) and docstrings within the src/ directory are read and processed by the agent and the scripts/gen-ref-pages.py script.
Boundary markers: Absent. There are no instructions or delimiters provided to prevent the agent from accidentally following instructions that might be embedded within the source code being documented.
Capability inventory: The skill allows the agent to modify the file system (writing to docs/reference/) and execute developer tools (mise, rumdl), which could be leveraged if the agent is manipulated by malicious content in a docstring.
Sanitization: No sanitization, filtering, or validation is performed on the source code content before it is processed by the agent.

rewrite-python-docs