The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources, specifically developer comments within Xcode String Catalogs and application source code files.
Ingestion points: Data enters the agent's context through the StringCatalogContext tool (which returns comment and sourceValues fields) and by reading source code files at paths specified in the usageLocations output of the context tool (as directed in SKILL.md, Step 2).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the workflow for these external data sources.
Capability inventory: The skill possesses the capability to modify project files through the StringCatalogEdit tool. It also uses the agent's primary file reading and shell capabilities to analyze source code.
Sanitization: The skill does not implement any filtering or sanitization of the content extracted from comments or source code before processing it.
[NO_CODE]: The skill consists entirely of markdown documentation, instructions, and language-specific reference files. No executable scripts (e.g., Python, JavaScript) or compiled binaries are included in the package.

translation