The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to parse external code, comments, and configurations to generate documentation. This creates a surface for indirect prompt injection if the source code contains malicious instructions intended to influence the agent's generation of documentation.
Ingestion points: resources/implementation-playbook.md describes extracting information from "code, configs, and comments" using ast.parse and ast.get_docstring.
Boundary markers: None identified in the provided templates; the skill relies on the agent's inherent safety filters.
Capability inventory: The skill generates file artifacts and documentation plans, and references CI/CD pipeline configuration.
Sanitization: There are no explicit sanitization routines for extracted docstrings before they are interpolated into the documentation output.
[EXTERNAL_DOWNLOADS]: The resources/implementation-playbook.md file contains HTML templates for Swagger UI that reference external CSS and JS files from cdn.jsdelivr.net. These are standard, well-known CDN references for documentation tools and are considered safe.
[COMMAND_EXECUTION]: The playbook includes example shell commands for installation (pip install), environment setup, and CI/CD triggers. These are presented as user-facing documentation templates rather than instructions for the agent to execute immediately, posing low risk in context.

code-documentation-doc-generate