The Agent Skills Directory

[SAFE]: The skill's primary function is to assist with documentation tasks using established standards like Google/NumPy docstrings, JSDoc, and OpenAPI. All provided code snippets and commands are standard developer tools and templates.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled source code to generate documentation, which is a standard attack surface. Malicious instructions hidden in code comments could attempt to influence the agent's output. No specific exploits were found in the skill's logic. * Ingestion points: The skill reads source code from the project to identify undocumented components. * Boundary markers: No explicit delimiters are used to separate code from instructions. * Capability inventory: The skill can read project files and modify them to add documentation. * Sanitization: No explicit input sanitization of processed source code is defined.

code-documenter