The Agent Skills Directory

[COMMAND_EXECUTION]: Executes shell commands via Bash to perform file system operations such as find, wc, and sort for analyzing codebase metrics like file size.
[PROMPT_INJECTION]: The skill processes external source code which could contain malicious instructions designed to manipulate the agent's behavior (Indirect Prompt Injection).
Ingestion points: Project files located in Assets/Scripts/ are accessed via Read and Grep tools in SKILL.md.
Boundary markers: Content from the project files is analyzed without explicit delimiters or instructions to ignore embedded commands.
Capability inventory: The agent has access to Edit, Write, and Bash tools across its lifecycle.
Sanitization: The skill does not perform sanitization or validation of the code content read from the file system.

Unity Refactor