The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches configuration guidelines and documentation from Sentry's official GitHub repository.
[COMMAND_EXECUTION]: Instructs the agent to use standard development tools and project-specific scripts, including npx skill-check for validating skill directories and npm run docs:update for maintaining documentation files.
[INDIRECT_PROMPT_INJECTION]: The skill processes various forms of external data, which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill reads Xcode project and workspace configurations, streams logs from simulators and physical devices, and reads all comments from GitHub issues.
Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to separate external data from system instructions.
Capability inventory: The skill possesses significant capabilities, including the ability to build and run code, execute LLDB debugging commands, and perform UI automation (gestures, text input) on devices.
Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested external content before it is processed by the agent.

xcodebuildmcp