The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation in references/mcp-setup.md provides instructions for the user to install the xcodebuildmcp and @smithery/cli packages using npx from the official npm registry. This is a standard setup procedure for Model Context Protocol (MCP) servers.
[COMMAND_EXECUTION]: The skill facilitates the execution of various development commands (e.g., xcodebuild, xcrun simctl, lldb) via the MCP server interface. These tools are used for project discovery, app compilation, and simulator management as intended by the skill's purpose.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from local project files, UI descriptions (mcp__xcodebuildmcp__describe_ui), and simulator logs (mcp__xcodebuildmcp__start_sim_log_cap). If these sources contain malicious instructions, they could potentially influence the agent's behavior. However, the risk is localized to the user's development environment.
Ingestion points: Project discovery outputs, UI element descriptions, and captured simulator/system logs.
Boundary markers: None explicitly defined in the skill instructions.
Capability inventory: File system discovery, application build/run execution, UI interaction (tap/type), and LLDB debugger command execution.
Sanitization: The skill does not explicitly define sanitization logic for data retrieved from the simulator or project metadata.

xcodebuildmcp