The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of local Python utilities, specifically validate-yaml.py and search-yaml.py, to validate documentation structure and search metadata. These tools are invoked within the local project context and are not sourced from external URLs.
[PROMPT_INJECTION]: The skill processes untrusted source code to generate documentation, presenting an indirect prompt injection risk.
Ingestion points: Source code files targeted for documentation in Phase 1 and Phase 2.
Boundary markers: Absent. There are no instructions provided to the agent to treat source code content as untrusted or to ignore embedded instructions.
Capability inventory: File system read access (source code), file system write access (documentation output), and execution of local Python validation scripts.
Sanitization: The skill utilizes validate-yaml.py to ensure output matches the expected YAML schema, but does not implement filtering or sanitization of the actual documentation content extracted from the code.

easysdd-libdoc