The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard shell utilities like find, ls, cat, and grep to perform static analysis of the project's structure and contents. These commands are limited to fact-gathering within the local codebase.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted file content from the codebase to generate documentation.
Ingestion points: Project manifests (package.json, requirements.txt, etc.), configuration files, and existing documentation are read from the repository.
Boundary markers: No explicit delimiters are used to wrap or isolate the data read from files during processing.
Capability inventory: The skill has the capability to create or modify the README.md file.
Sanitization: There is no mention of sanitizing or validating extracted data before including it in the generated content.

readme-reviewer