The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute bundle exec rubocop and its variants to lint and auto-correct Ruby code. These are standard operations for Ruby development environments.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it reads project configuration files (.rubocop.yml) and Ruby source code.
Ingestion points: Reads .rubocop.yml, .rubocop_todo.yml, and various Ruby files (e.g., app/models/user.rb) via the Bash and Read tools.
Boundary markers: The instructions do not explicitly define delimiters to distinguish between code content and instructions, though it treats the files as configuration/data to be processed by Rubocop.
Capability inventory: The skill has Read, Write, Edit, and Bash capabilities, allowing it to modify files and execute local commands.
Sanitization: There is no explicit sanitization of the file content before the agent processes the Rubocop output or modifies files.

rubocop-fixer