The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown-based instructions and reference materials. No executable code or suspicious automation patterns were identified within the skill structure.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze local project files, which is an expected behavior for a development-focused tool. This constitutes an ingestion point for untrusted data, but it is necessary for the skill's primary function.
Ingestion points: The skill explicitly directs the agent to use Read and Grep operations on project files like Package.swift and project.pbxproj to determine environment settings.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content read from user projects.
Capability inventory: The skill enables the agent to suggest code refactors, fix concurrency warnings, and provide architectural guidance.
Sanitization: There are no specific instructions for the agent to sanitize or validate the content of the project files it reads before processing.

swift-concurrency