The Agent Skills Directory

[SAFE]: The skill uses localized tools for iOS development and does not communicate with untrusted external servers or perform unauthorized actions.
[COMMAND_EXECUTION]: The skill utilizes the XcodeBuildMCP toolset to perform system-level actions like building iOS projects and controlling the simulator. These actions are triggered by user commands for development purposes.
[DATA_EXPOSURE]: The agent is capable of reading simulator logs and capturing screenshots. This data access is essential for its primary function of debugging and is restricted to the local development environment.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes external data.
Ingestion points: Application logs via mcp__XcodeBuildMCP__start_sim_log_cap and UI metadata via mcp__XcodeBuildMCP__describe_ui.
Boundary markers: Not present.
Capability inventory: Local tool execution including building and running code via mcp__XcodeBuildMCP__build_run_sim and UI interactions via mcp__XcodeBuildMCP__tap and mcp__XcodeBuildMCP__type_text.
Sanitization: None specified for ingested logs or UI text. Given the context of a local developer tool, this risk is considered low and associated with primary functionality.

ios-debugger-agent